Tootfinder

Learning to optimize convex risk measures: The cases of utility-based shortfall risk and optimized certainty equivalent risk
Sumedh Gupte, Prashanth L. A., Sanjay P. Bhat
https://arxiv.org/abs/2506.01101

Learning to optimize convex risk measures: The cases of utility-based shortfall risk and optimized certainty equivalent risk
We consider the problems of estimation and optimization of two popular convex risk mea- sures: utility-based shortfall risk (UBSR) and Optimized Certainty Equivalent (OCE) risk. We extend these risk measures to cover possibly unbounded random variables. We cover prominent risk measures like the entropic risk, expectile risk, monotone mean-variance risk, Value-at-Risk, and Conditional Value-at-Risk as few special cases of either the UBSR or the OCE risk. In the context of estimation, we derive n…

Developing a Risk Identification Framework for Foundation Model Uses
David Piorkowski, Michael Hind, John Richards, Jacquelyn Martino
https://arxiv.org/abs/2506.02066

Developing a Risk Identification Framework for Foundation Model Uses
As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and cataloging them in AI risk taxonomies, there is little guidance for practitioners on how to determine which risks are relevant for a given foundation model use. In this paper, we address this gap and develop requirements and an initial design for a risk iden…

Improved Risk Ratio Approximation by Complementary Log-Log Models: A Comparison with Logistic Models
Yuji Tsubota, Kenji Beppu
https://arxiv.org/abs/2506.00889

Improved Risk Ratio Approximation by Complementary Log-Log Models: A Comparison with Logistic Models
Odds ratios obtained from logistic models fail to approximate risk ratios with common outcomes, leading to potential misinterpretations about exposure effects by practitioners. This article investigates the complementary log-log models as a practical alternative to produce risk ratio approximation. We demonstrate that the corresponding effect measure of complementary log-log models, called the complementary log ratio in this article, consistently provides a closer approximation to risk ratios t…

Trump Wants to Cut Tribal College Funding by Nearly 90%,
Putting Them at Risk of Closing
ProPublica found that Congress was underfunding tribal colleges by a quarter-billion dollars per year.
Rather than fixing the problem, proposed federal funding cuts unveiled this week would devastate the schools, tribal education leaders say

Trump Wants to Cut Tribal College Funding by Nearly 90%, Putting Them at Risk of Closing
ProPublica found that Congress was underfunding tribal colleges by a quarter-billion dollars per year. Rather than fixing the problem, proposed federal funding cuts unveiled this week would devastate the schools, tribal education leaders say.

Analysis – When your LLM calls the cops: Claude 4’s whistle-blow and the new agentic AI risk stack
🤖 https://venturebeat.com/ai/when-your-llm-calls-the-cops-claude-4s-whistle-blow-and-the-new-agentic-ai-risk-stack/…

When your LLM calls the cops: Claude 4’s whistle-blow and the new agentic AI risk stack
Claude 4’s “whistle-blow” surprise shows why agentic AI risk lives in prompts and tool access, not benchmarks. Learn the 6 controls every enterprise must adopt.

masks at protests / demographics 2/n
I wonder about the influence of employment, as well. If you're at risk every work day, I could well imagine it seeming pointless to start being careful the rest of the time, and maybe just too cognitively dissonant to consider.
I remember in 2020, someone I knew was working at Waterstones, and they were forbidden to mask up at work - even though 2020 was before the whole "covid is over" thing.
I also remember reading about someone - maybe a nurse? that _kind_ of job, anyway - who'd started wearing a fitted mask while the default in their workplace was baggy blues, and iirc was formally rebuked. It wasn't allowed.
If for whatever reason you're unable to hold down a typical job, you might not have much cash for _getting_ things like masks, but you're also not under that same kind of economic pressure to put yourself at risk.
#masks #work #CovidIsntOver

Computational adversarial risk analysis for general security games
Jose Manuel Camacho, Roi Naveiro, David Rios Insua
https://arxiv.org/abs/2506.02603 http…

Computational adversarial risk analysis for general security games
This paper provides an efficient computational scheme to handle general security games from an adversarial risk analysis perspective. Two cases in relation to single-stage and multi-stage simultaneous defend-attack games motivate our approach to general setups which uses bi-agent influence diagrams as underlying problem structure and augmented probability simulation as core computational methodology. Theoretical convergence and numerical, modeling, and implementation issues are thoroughly discu…

AI coding startups are at risk of being disrupted by Google, Microsoft, and OpenAI; source: Microsoft's GitHub Copilot grew to over $500M in revenue last year (Reuters)
https://www.reuters.com/business/ai-vibe-codi…

"Childhood cancer survivors have >2x risk of melanoma compared to the general population and those with an invasive melanoma have>2x risk of death."
https://ascopubs.org/doi/abs/10.1200/JCO-24-01519

This https://arxiv.org/abs/2505.13556 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning Collision Risk from Naturalistic Driving with Generalised Surrogate Safety Measures
Accurate and timely alerts for drivers or automated systems to unfolding collisions remains a challenge in road safety, particularly in highly interactive urban traffic. Existing approaches require labour-intensive annotation of sparse risk, struggle to consider varying contextual factors, or are useful only in the scenarios they are designed for. To address these limits, this study introduces the generalised surrogate safety measure (GSSM), a new approach that learns exclusively from naturalis…

Faced with the growing risk that #LightPollution represents for the development of astronomy in Chile, international observatories with a presence in the country have formed a joint organization dedicated to protecting the dark skies of northern Chile: https://giantmagellan.org/2025/06/03/dark-skies-council-international-astronomical-observatories-join-forces-to-protect-chiles-skies/ - the Association of Universities for Research in Astronomy (AURA), the Giant Magellan Telescope, the European Southern Observatory (ESO) and Carnegie Science’s Las Campanas Observatory (LCO), signed an agreement to create the Dark Skies Council; through this alliance, the institutions will work in a coordinated manner to protect Chile’s privileged skies.

This https://arxiv.org/abs/2505.09880 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Determining Absence of Unreasonable Risk: Approval Guidelines for an Automated Driving System Deployment
This paper provides an overview of how the determination of absence of unreasonable risk can be operationalized. It complements previous theoretical work published by existing developers of Automated Driving Systems (ADS) on the overall engineering practices and methodologies for readiness determination. Readiness determination is, at its core, a risk assessment process. It is aimed at evaluating the residual risk associated with a new deployment. The paper proposes methodological criteria to g…

Balancing Profit and Fairness in Risk-Based Pricing Markets
Jesse Thibodeau, Hadi Nekoei, Afaf Ta\"ik, Janarthanan Rajendran, Golnoosh Farnadi
https://arxiv.org/abs/2506.00140

Balancing Profit and Fairness in Risk-Based Pricing Markets
Dynamic, risk-based pricing can systematically exclude vulnerable consumer groups from essential resources such as health insurance and consumer credit. We show that a regulator can realign private incentives with social objectives through a learned, interpretable tax schedule. First, we provide a formal proposition that bounding each firm's \emph{local} demographic gap implicitly bounds the \emph{global} opt-out disparity, motivating firm-level penalties. Building on this insight we introduce …

This https://arxiv.org/abs/2411.13111 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Optimal investment problem in a renewal risk model with generalized Erlang distributed interarrival times
This paper explores the optimal investment problem of a renewal risk model with generalized Erlang distributed interarrival times. The phases of the Erlang interarrival time is assumed to be observable. The price of the risky asset is driven by the constant elasticity of variance model (CEV) and the insurer aims to maximize the exponential utility of the terminal wealth by asset allocation. By solving the corresponding Hamilton-Jacobi-Bellman (HJB) equation, we establish the concavity of the va…

Trump Wants to Cut Tribal College Funding by Nearly 90%, Putting Them at Risk of Closing (Matt Krupnick/ProPublica)
https://www.propublica.org/article/tribal-colleges-universities-trump-cuts-funding
http://www.memeorandum.com/250603/p110#a250603p110

At the risk of repeating myself repeatedly: Peace Orchestra, Who Am I. #sound
https://www.youtube.com/watch?v=SG5BVxImD8o

This https://arxiv.org/abs/2505.22784 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Split the Yield, Share the Risk: Pricing, Hedging and Fixed rates in DeFi
We present the first formal treatment of \emph{yield tokenization}, a mechanism that decomposes yield-bearing assets into principal and yield components to facilitate risk transfer and price discovery in decentralized finance (DeFi). We propose a model that characterizes yield token dynamics using stochastic differential equations. We derive a no-arbitrage pricing framework for yield tokens, enabling their use in hedging future yield volatility and managing interest rate risk in decentralized l…

I honestly don’t get how this is possible in 2025.
There’s no excuse for not having protected backups of everything critical. That was true 30 years ago, it is true today. Back then a bigger piece of the risk was hardware, less malware. Today it is unlikely for a disk failure to take your data because we all learned that RAID was worthwhile. But RAID is not a backup and backups today need to be resistant to intentional malicious deletion.

SIL Allocation for Mitigation Safety Functions
Hamid Jahanian
https://arxiv.org/abs/2506.02309 https://arxiv.org/pdf/2506.02309

SIL Allocation for Mitigation Safety Functions
SIL (Safety Integrity Level) allocation plays a pivotal role in evaluating the significance of Safety Functions (SFs) within high-risk industries. The outcomes of a SIL allocation study determine the design specifications necessary to uphold the Probability of Failure on Demand (PFD) below permissible limits, thus managing risk effectively. While extensive research has focused on SIL allocation for preventive SFs, there is a noticeable gap in attention towards mitigation SFs. To address this ga…

Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work
Alice Qian Zhang, Ryland Shaw, Laura Dabbish, Jina Suh, Hong Shen
https://arxiv.org/abs/2505.24246

Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work
As AI systems are increasingly tested and deployed in open-ended and high-stakes domains, crowd workers are often tasked with responsible AI (RAI) content work. These tasks include labeling violent content, moderating disturbing text, or simulating harmful behavior for red teaming exercises to shape AI system behaviors. While prior efforts have highlighted the risks to worker well-being associated with RAI content work, far less attention has been paid to how these risks are communicated to wor…

Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
Ananya Omanwar, Fady Alajaji, Tam\'as Linder
https://arxiv.org/abs/2505.24117

Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
Given finite-dimensional random vectors $Y$, $X$, and $Z$ that form a Markov chain in that order (i.e., $Y \to X \to Z$), we derive upper bounds on the excess minimum risk using generalized information divergence measures. Here, $Y$ is a target vector to be estimated from an observed feature vector $X$ or its stochastically degraded version $Z$. The excess minimum risk is defined as the difference between the minimum expected loss in estimating $Y$ from $X$ and from $Z$. We present a family of …

Filing: OpenAI seeks to block a May 13 court order requiring it to preserve all ChatGPT logs, including deleted chats, arguing it poses a risk to users' privacy (Ashley Belanger/Ars Technica)
https://arstechnica.com/tech-policy/20

OpenAI slams court order to save all ChatGPT logs, including deleted chats
OpenAI defends privacy of hundreds of millions of ChatGPT users.

Privacy-Aware, Public-Aligned: Embedding Risk Detection and Public Values into Scalable Clinical Text De-Identification for Trusted Research Environments
Arlene Casey, Stuart Dunbar, Franz Gruber, Samuel McInerney, Mat\'u\v{s} Falis, Pamela Linksted, Katie Wilde, Kathy Harrison, Alison Hamilton, Christian Cole
https://arxiv.…

Privacy-Aware, Public-Aligned: Embedding Risk Detection and Public Values into Scalable Clinical Text De-Identification for Trusted Research Environments
Clinical free-text data offers immense potential to improve population health research such as richer phenotyping, symptom tracking, and contextual understanding of patient care. However, these data present significant privacy risks due to the presence of directly or indirectly identifying information embedded in unstructured narratives. While numerous de-identification tools have been developed, few have been tested on real-world, heterogeneous datasets at scale or assessed for governance read…

heise | heise Update vom 30. Mai 2025: Lesetipps fürs Wochenende
Der wöchentliche Newsletter von heise mit Schutz vor "Human Risk", Steuer-Apps, Deutschland-Stack, Synology-RAID nachbilden, Gefahr von Online-Glücksspiel

Machine-learning Growth at Risk
Tobias Adrian, Hongqi Chen, Max-Sebastian Dov\`i, Ji Hyung Lee
https://arxiv.org/abs/2506.00572 https://

Machine-learning Growth at Risk
We analyse growth vulnerabilities in the US using quantile partial correlation regression, a selection-based machine-learning method that achieves model selection consistency under time series. We find that downside risk is primarily driven by financial, labour-market, and housing variables, with their importance changing over time. Decomposing downside risk into its individual components, we construct sector-specific indices that predict it, while controlling for information from other sectors…

This https://arxiv.org/abs/2407.14272 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Global Balance and Systemic Risk in Financial Correlation Networks
The global balance index is used in the network literature to quantify how balanced a signed network is. In this paper we show that the global balance index of financial correlation networks can be used as a systemic risk measure. We define the global balance index of a network starting from a diffusive process that describes how the information spreads across nodes in a network, providing an alternative derivation to the usual combinatorial one. The steady state of this process is the solution…

Drawdowns, Drawups, and Occupation Times under General Markov Models
Pingping Zeng, Gongqiu Zhang, Weinan Zhang
https://arxiv.org/abs/2506.00552 https://…

Drawdowns, Drawups, and Occupation Times under General Markov Models
Drawdown risk, an important metric in financial risk management, poses significant computational challenges due to its highly path-dependent nature. This paper proposes a unified framework for computing five important drawdown quantities introduced in Landriault et al. (2015) and Zhang (2015) under general Markov models. We first establish linear systems and develop efficient algorithms for such problems under continuous-time Markov chains (CTMCs), and then establish their theoretical convergen…

STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain
Ziwon Yoon, Lawrence Y. Zhu, Lu Gan, Ye Zhao
https://arxiv.org/abs/2506.01046

STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain
Bipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile plarforms such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has instead relied on manually designed rules with limited consideration of locomotion stability on rough terrain. In this work, we present the first learning-based traversability estimation and risk-sensitive…

This https://arxiv.org/abs/2502.15865 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk
Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy. We argue that accuracy metrics and return-based scores provide an illusion of reliability, overlooking vulnerabilities such as hallucinated facts, stale data, and adversarial prompt manipulation. We take a firm position: financial LLM agents should be evaluated first and foremost on their risk profile, not on their point-estimate performance. Drawing…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
Jingyi Yang, Shuai Shao, Dongrui Liu, Jing Shao
https://arxiv.org/abs/2506.00618 https://…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

Systematic Hazard Analysis for Frontier AI using STPA
Simon Mylius
https://arxiv.org/abs/2506.01782 https://arxiv.org/pdf/2506.01782

Systematic Hazard Analysis for Frontier AI using STPA
All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk modelling, based on established practices used in safety-critical industries, has been recommended, however frontier AI companies currently do not describe in detail any structured approach to identifying and analysing hazards. STPA (Systems-Theoretic Process A…

GenDMR: A dynamic multimodal role-swapping network for identifying risk gene phenotypes
Lina Qin, Cheng Zhu, Chuqi Zhou, Yukun Huang, Jiayi Zhu, Ping Liang, Jinju Wang, Yixing Huang, Cheng Luo, Dezhong Yao, Ying Tan
https://arxiv.org/abs/2506.01456

GenDMR: A dynamic multimodal role-swapping network for identifying risk gene phenotypes
Recent studies have shown that integrating multimodal data fusion techniques for imaging and genetic features is beneficial for the etiological analysis and predictive diagnosis of Alzheimer's disease (AD). However, there are several critical flaws in current deep learning methods. Firstly, there has been insufficient discussion and exploration regarding the selection and encoding of genetic information. Secondly, due to the significantly superior classification value of AD imaging features com…

Cost of institutional incentives for promoting cooperation in $2\times2$ games and collective risk games
M. H. Duong, C. M. Durbac, T. A. Han
https://arxiv.org/abs/2506.02968

Cost of institutional incentives for promoting cooperation in $2\times2$ games and collective risk games
Prosocial behaviours, which appear to contradict Darwinian principles of individual payoff maximisation, have been extensively studied across multiple disciplines. Cooperation, requiring a personal cost for collective benefits, is widespread in nature and has been explained through mechanisms such as kin selection, direct and indirect reciprocity, and network reciprocity. Institutional incentives, which reward cooperation and punish anti-social behaviour, offer a promising approach to fostering…

This https://arxiv.org/abs/2410.03096 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Expected value of sample information calculations for risk prediction model development
Risk prediction models are often advertised as deterministic functions that map covariates to predicted risks. However, they are typically trained using finite samples, and as such, their predictions are inherently uncertain. This uncertainty has been addressed in terms of uncertainty around metrics of model performance (e.g., confidence intervals around c-statistic), as well as uncertainty or instability of predictions. Correspondingly, sample size calculations for model development studies ta…

masks at protests / demographics
Interestingly, at the May Day gathering I was the only one in a mask.
Thinking about the contrast with the trans protest the other week, where "good" (fitted not floppy) masks were dotted about throughout the crowd, and felt normalised.
Today's march was a less crowded event than the trans protest, so pretty low-risk for covid transmission anyway. But then when we got to the mini-fair after the march, indoors at the Friends' Meeting House, I didn't see anyone masking indoors either.
I wonder about the demographics of that difference. Seems like there's a traditional union/Labour left who share the mainstream denial of present-day covid, and a statistically more disabled & marginalised cohort where trans awareness and disability/illness awareness overlap.
#masks #CovidIsntOver

Exercise can reduce the risk of cancer patients dying by a third,
stop tumours coming back
and is even more effective than drugs,
according to the results of a landmark trial that could transform health guidelines worldwide.

Predictability of quantum observables: Applications in QKD and top quarks
Dennis I. Mart\'inez-Moreno, Miguel Castillo-Celeita, Diego G. Bussandri
https://arxiv.org/abs/2505.24502

Predictability of quantum observables: Applications in QKD and top quarks
We quantify and optimize the predictability of local observables in bipartite quantum systems by employing the Bayes risk and the inference variance, two measures rooted in statistical learning theory. Specifically, we minimized these quantities when the prediction is improved by an additional quantum system, providing analytical expressions for arbitrary two-qubit states, and showcasing a connection with Einstein-Podolsky-Rosen steering criteria. Then, we embed our Bayes risk minimization into…

Get me out of this hole: a profile likelihood approach to identifying and avoiding inferior local optima in choice models
Stephane Hess, David Bunch, Andrew Daly
https://arxiv.org/abs/2506.02722

Get me out of this hole: a profile likelihood approach to identifying and avoiding inferior local optima in choice models
Choice modellers routinely acknowledge the risk of convergence to inferior local optima when using structures other than a simple linear-in-parameters logit model. At the same time, there is no consensus on appropriate mechanisms for addressing this issue. Most analysts seem to ignore the problem, while others try a set of different starting values, or put their faith in what they believe to be more robust estimation approaches. This paper puts forward the use of a profile likelihood approach t…

Honey Revenge - Risk (Official Music Video)
#music

This https://arxiv.org/abs/2506.01046 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain
Bipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile plarforms such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has instead relied on manually designed rules with limited consideration of locomotion stability on rough terrain. In this work, we present the first learning-based traversability estimation and risk-sensitive…

Drowning in infosec news overload? Check out today's Metacurity for a concise rundown of the most critical developments you should know, including
--UK military will ramp up offensive cyber attacks against Russia and China
--Victoria's Secret hit by cyberattack,
--LexisNexis Risk Solutions breach affects 364K,
--Procurement database exposed Russian nuclear bases to attack,
--US gov't to mix DNA data of migrant children and sex offenders,
--ASUS …

UK military will ramp up offensive cyber attacks against Russia and China
Victoria's Secret hit by cyberattack, LexisNexis risk arm breach affects 364K, Procurement database exposed Russian nuclear bases to attack, US gov't to mix DNA data of migrant children and sex offenders, ASUS routers ensnared by novel botnet, APT41 exploited Google Calendar, much more

Investment Risk for Energy Infrastructure Construction Is Highest for #NuclearPower Plants, Lowest for #Solar

Investment Risk for Energy Infrastructure Construction Is Highest for Nuclear Power Plants, Lowest for Solar - CleanTechnica
A new study from the Boston University Institute for Global Sustainability finds that construction costs run over budget for more than 60% of energy infrastructure projects worldwide. By Laura Hurley Between now and 2050, the International Energy Agency projects that more than $100 trillion will be spent on building net-zero energy infrastructure globally. ... [continued]

This https://arxiv.org/abs/2407.04503 has been replaced.
initial toot: https://mastoxiv.page/@arX…

When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings
As large language models (LLMs) start interacting with each other and generating an increasing amount of text online, it becomes crucial to better understand how information is transformed as it passes from one LLM to the next. While significant research has examined individual LLM behaviors, existing studies have largely overlooked the collective behaviors and information distortions arising from iterated LLM interactions. Small biases, negligible at the single output level, risk being amplifi…

I'd be interested in how well "hand over all the data or be fired" will work in a country without a presidential override for legislation.
https://www.theguardian.com/politics/2025/jun/02/reform-uk-to-pilot-doge-…

So i just threw together a first iteration of the switch engine PCB schematic in one crazed allnighter (thanks non 24 hour sleep schedules lol, its 0900 and I'm almost ready for bed).
It's missing some details like mounting holes and such, plus a few odds and ends like a 2.5V LDO and level shifter on the rs232 console, but I think it's 80% or so done. Lots of copy paste from kup-lulz and lcbringup which was of course the intent, those projects were intended to de-risk the s…

This https://arxiv.org/abs/2503.14328 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Risk-Sensitive Model Predictive Control for Interaction-Aware Planning -- A Sequential Convexification Algorithm
This paper considers risk-sensitive model predictive control for stochastic systems with a decision-dependent distribution. This class of systems is commonly found in human-robot interaction scenarios. We derive computationally tractable convex upper bounds to both the objective function, and to frequently used penalty terms for collision avoidance, allowing us to efficiently solve the generally nonconvex optimal control problem as a sequence of convex problems. Simulations of a robot navigatin…

yeah my worst character trait is being too risk averse, over the last year ive been constantly doing things i should have done like 6 years ago

Visualization for interactively adjusting the de-bias effect of word embedding
Arisa Sugino, Takayuki Itoh
https://arxiv.org/abs/2506.02447 https://…

Visualization for interactively adjusting the de-bias effect of word embedding
Word embedding, which converts words into numerical values, is an important natural language processing technique and widely used. One of the serious problems of word embedding is that the bias will be learned and affect the model if the dataset used for pre-training contains bias. On the other hand, indiscriminate removal of bias from word embeddings may result in the loss of information, even if the bias is undesirable to us. As a result, a risk of model performance degradation due to bias re…

This https://arxiv.org/abs/2505.23436 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Emergent Risk Awareness in Rational Agents under Resource Constraints
Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have resource or failure constraints where action sequences may be forcibly terminated once resources are exhausted, agents face implicit trade-offs that reshape their utility-driven (rational) behaviour. Additionally, since these agents are typically commissioned by a h…

This https://arxiv.org/abs/2502.09716 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Principles and Policy Recommendations for Comprehensive Genetic Data Governance
Genetic data collection has become ubiquitous, producing genetic information about health, ancestry, and social traits. However, unregulated use, especially amid evolving scientific understanding, poses serious privacy and discrimination risks. These risks are intensified by advancing AI, particularly multi-modal systems integrating genetic, clinical, behavioral, and environmental data. In this work, we organize the uses of genetic data along four distinct "pillars", and develop a risk assessme…

Prediction of the Conditional Probability Densities of Time Interval Extrema for Risk-Sensitive Scheduling
Buyi Yu, Wenyuan Tang
https://arxiv.org/abs/2506.01358

Prediction of the Conditional Probability Densities of Time Interval Extrema for Risk-Sensitive Scheduling
Planning and scheduling activities in the electrical power system, such as the commitment of reserve generation, often involve statistical characterization of peak demand. Extreme Value Analysis (EVA)-based probabilistic assessments of annual peaks are widely adopted by energy regulatory and oversight agencies to determine the likelihood and severity of potential energy shortfalls. Due to the inability of classical EVA to account for peak distributions that change with annual extreme temperatur…

The good news is, you won’t care….
Also, the study was only 55 people.
#cannabis
https://www.yahoo.com/news/smoking-marijuana-eating-cannab…

Smoking marijuana and eating cannabis gummies both linked to dangerous health risk, study finds
Experts warn of cardiovascular risks from chronic cannabis use, as a UC San Francisco study shows similar vascular effects to tobacco, urging caution.

LexisNexis Risk Solutions says 364,000 impacted by breach involving GitHub data https://therecord.media/lexis-nexis-breach-hundreds-thousands

This https://arxiv.org/abs/2504.15395 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Measuring likelihood in cybersecurity
In cybersecurity risk is commonly measured by impact and probability, the former is objectively measured based on the consequences from the use of technology to obtain business gains, or by achieving business objectives. The latter has been measured, in sectors such as financial or insurance, based on historical data because there is vast information, and many other fields have applied the same approach. Although in cybersecurity, as a new discipline, there is not always historical data to supp…

Several significant pieces of the House-approved spending bill are at risk of falling out of the legislation as it moves through the Senate
At least one of Thune’s members is already publicly floating that his party should be willing to directly overrule Senate Parlementarian MacDonough on the reconciliation bill.
In a tweet last month, Sen. Mike Lee (R-Utah) wrote on X that “disagreeing with the Senate parliamentarian may be warranted if the parliamentarian gives bad advice, and …

Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation
Yuan Gan, Jiaxu Miao, Yunze Wang, Yi Yang
https://arxiv.org/abs/2506.01591

Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation
Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence, addressing these ethical concerns has become a pressing issue in AI security. Recent proactive defense studies focused on countering LDM-based models by adding perturbations to portraits. However, th…

Computer scientist Greg Nelson and I presented "Following AI's Footsteps from School to Society" at the 2025 UMaine Faculty Institute https://mycampus.maine.edu/web/uc-faculty-portal/faculty-institute-2025 including the IMPACT RISK framew…

[2025-06-03 Tue (UTC), no new articles found for q-fin.RM Risk Management]
#toXiv_bot_toot

This https://arxiv.org/abs/2506.01220 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Vulnerability Management Chaining: An Integrated Framework for Efficient Cybersecurity Risk Prioritization
Cybersecurity teams face an overwhelming vulnerability crisis: with 25,000+ new CVEs disclosed annually, traditional CVSS-based prioritization requires addressing 60% of all vulnerabilities while correctly identifying only 20% of those actually exploited. We propose Vulnerability Management Chaining, an integrated decision tree framework combining historical exploitation evidence (KEV), predictive threat modeling (EPSS), and technical impact assessment (CVSS) to transform vulnerability manageme…

Estimating a regression function under possible heteroscedastic and heavy-tailed errors. Application to shape-restricted regression
Yannick Baraud, Guillaume Maillard
https://arxiv.org/abs/2506.00852

Estimating a regression function under possible heteroscedastic and heavy-tailed errors. Application to shape-restricted regression
We consider a regression framework where the design points are deterministic and the errors possibly non-i.i.d. and heavy-tailed (with a moment of order $p$ in $[1,2]$). Given a class of candidate regression functions, we propose a surrogate for the classical least squares estimator (LSE). For this new estimator, we establish a nonasymptotic risk bound with respect to the absolute loss which takes the form of an oracle type inequality. This inequality shows that our estimator possesses natural …

This https://arxiv.org/abs/2505.23397 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy
This article presents a structured framework for Human-AI collaboration in Security Operations Centers (SOCs), integrating AI autonomy, trust calibration, and Human-in-the-loop decision making. Existing frameworks in SOCs often focus narrowly on automation, lacking systematic structures to manage human oversight, trust calibration, and scalable autonomy with AI. Many assume static or binary autonomy settings, failing to account for the varied complexity, criticality, and risk across SOC tasks c…

Prenatal phthalate exposures and adiposity outcomes trajectories: a multivariate Bayesian factor regression approach
Phuc H. Nguyen, Stephanie M. Engel, Amy H. Herring
https://arxiv.org/abs/2506.02518

Prenatal phthalate exposures and adiposity outcomes trajectories: a multivariate Bayesian factor regression approach
We aim to assess the longitudinal effects of prenatal exposure to phthalates on the risk of childhood obesity in children aged 4 to 7, with potential time-varying and sex-specific effects. Multiple body-composition-related outcomes, such as BMI z-score, fat mass percentage, and waist circumference, are available in the data. Existing chemical mixture analyses often look at these outcomes individually due to the limited availability of multivariate models for mixture exposures. We propose a mult…

This https://arxiv.org/abs/2503.03480 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and humans. How can safety constraints be explicitly integrated into VLAs? We address this by exploring an integrated safety approach (ISA), systematically modeling safety requirements, then actively eliciting diverse unsafe behaviors, effectively constraining VLA poli…

Winners vs. Losers: Momentum-based Strategies with Intertemporal Choice for ESG Portfolios
Ayush Jha, Abootaleb Shirvani, Ali Jaffri, Svetlozar T. Rachev, Frank J. Fabozzi
https://arxiv.org/abs/2505.24250

Winners vs. Losers: Momentum-based Strategies with Intertemporal Choice for ESG Portfolios
This paper introduces a state-dependent momentum framework that integrates ESG regime switching with tail-risk-aware reward-risk metrics. Using a dynamic programming approach and solving a finite-horizon Bellman equation, we construct long-short momentum portfolios that adjust to changing ESG sentiment regimes. Unlike traditional momentum strategies based on historical returns, our approach incorporates the Stable Tail Adjusted Return ratio and Rachev ratio to better capture downside risk in tu…

Singularity Protocol for Cross Chain AMM without Intermediate Tokens or Bridges
Sumit Vohra
https://arxiv.org/abs/2505.24337 https://…

Singularity Protocol for Cross Chain AMM without Intermediate Tokens or Bridges
Automated Market Makers (AMMs) are decentralized exchange protocols that provide continuous access to token liquidity without the need for order books or traditional market makers. However, this innovation has failed to scale when it comes to cross-chain swaps. Modern cross-chain swaps employ double-sided AMMs, which are not only inefficient due to liquidity fragmentation but also require an intermediate token. This introduces inherent volatility risk as well as blockchain and bridging risk, es…

Replication of Reference-Dependent Preferences and the Risk-Return Trade-Off in the Chinese Market
Penggan Xu
https://arxiv.org/abs/2505.20608 https://

Replication of Reference-Dependent Preferences and the Risk-Return Trade-Off in the Chinese Market
This study replicates the findings of Wang et al. (2017) on reference-dependent preferences and their impact on the risk-return trade-off in the Chinese stock market, a unique context characterized by high retail investor participation, speculative trading behavior, and regulatory complexities. Capital Gains Overhang (CGO), a proxy for unrealized gains or losses, is employed to explore how behavioral biases shape cross-sectional stock returns in an emerging market setting. Utilizing data from 1…

Evaluating financial tail risk forecasts: Testing Equal Predictive Ability
Lukas Bauer
https://arxiv.org/abs/2505.23333 https://arxiv…

Evaluating financial tail risk forecasts: Testing Equal Predictive Ability
This paper provides comprehensive simulation results on the finite sample properties of the Diebold-Mariano (DM) test by Diebold and Mariano (1995) and the model confidence set (MCS) testing procedure by Hansen et al. (2011) applied to the asymmetric loss functions specific to financial tail risk forecasts, such as Value-at-Risk (VaR) and Expected Shortfall (ES). We focus on statistical loss functions that are strictly consistent in the sense of Gneiting (2011a). We find that the tests show lit…

COVID before or during pregnancy may confer 2 to 3 times the risk of miscarriage:
https://www.cidrap.umn.edu/covid-19/covid-or-during-pregnancy-may-confer-2-3-times-risk-miscarriage

FPF and OneTrust launch updated Conformity Assessment under the EU AI Act: guide and infographic
https://fpf.org/blog/fpf-and-onetrust-launch-updated-conformity-assessment-under-the-eu-ai-act-guide-and-infographi…

Machine learning approach to stock price crash risk
Abdullah Karasan, Ozge Sezgin Alp, Gerhard-Wilhelm Weber
https://arxiv.org/abs/2505.16287 https://

Machine learning approach to stock price crash risk
In this study, we propose a novel machine-learning-based measure for stock price crash risk, utilizing the minimum covariance determinant methodology. Employing this newly introduced dependent variable, we predict stock price crash risk through cross-sectional regression analysis. The findings confirm that the proposed method effectively captures stock price crash risk, with the model demonstrating strong performance in terms of both statistical significance and economic relevance. Furthermore,…

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Kalyan Nakka, Nitesh Saxena
https://arxiv.org/abs/2506.02479

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignment of LLMs. However, the robustness of these aligned LLMs is always challenged by adversarial attacks that exploit unexplored and underlying vulnerabilities of the safety alignment. In this paper, we …

DuAL-Net: A Hybrid Framework for Alzheimer's Disease Prediction from Whole-Genome Sequencing via Local SNP Windows and Global Annotations
Eun Hye Lee, Taeho Jo
https://arxiv.org/abs/2506.00673

DuAL-Net: A Hybrid Framework for Alzheimer's Disease Prediction from Whole-Genome Sequencing via Local SNP Windows and Global Annotations
Alzheimer's disease (AD) dementia is the most common form of dementia. With the emergence of disease-modifying therapies, predicting disease risk before symptom onset has become critical. We introduce DuAL-Net, a hybrid deep learning framework for AD dementia prediction using whole genome sequencing (WGS) data. DuAL-Net integrates two components: local probability modeling, which segments the genome into non-overlapping windows, and global annotation-based modeling, which annotates SNPs and reo…

Internal docs show Meta plans to use AI to automate up to 90% of its privacy and integrity risk assessments, including in sensitive areas like violent content (NPR)
https://www.npr.org/2025/05/31/nx-s1-5407870/meta-ai-facebook-instagram-risks…

[2025-06-04 Wed (UTC), no new articles found for q-fin.RM Risk Management]
#toXiv_bot_toot

A new COVID subvariant spreads rapidly as Trump pivots away from vaccines
A new, highly transmissible COVID subvariant has been detected in California
— heightening the risk of a potential summer wave
as recent moves by the Trump administration threaten to make vaccines harder to get,
and more expensive,
for many Americans,
some health experts warn.
Health and Human Services Secretary Robert F. Kennedy Jr.
announced this week that he was resci…

COVID variant NB.1.8.1 spreads as Trump pivots away from vaccines
A new, highly transmissible COVID subvariant has been detected in California — heightening the risk of a summer wave as recent moves by the Trump administration threaten to make vaccines harder to get, and more expensive, for many Americans, some health experts warn.

Factorized Tail Volatility Model: Augmenting Excess-over-Threshold Method for High-Dimensional Hevay-Tailed Data
Yifan Hu, Yanxi Hou
https://arxiv.org/abs/2506.00840

Factorized Tail Volatility Model: Augmenting Excess-over-Threshold Method for High-Dimensional Hevay-Tailed Data
Ecess-over-Threshold method is a crucial technique in extreme value analysis, which approximately models larger observations over a threshold using a Generalized Pareto Distribution. This paper presents a comprehensive framework for analyzing tail risk in high-dimensional data by introducing the Factorized Tail Volatility Model (FTVM) and integrating it with central quantile models through the EoT method. This integrated framework is termed the FTVM-EoT method. In this framework, a quantile-rel…

Split the Yield, Share the Risk: Pricing, Hedging and Fixed rates in DeFi
Viraj Nadkarni, Pramod Viswanath
https://arxiv.org/abs/2505.22784 https://…

Split the Yield, Share the Risk: Pricing, Hedging and Fixed rates in DeFi
We present the first formal treatment of \emph{yield tokenization}, a mechanism that decomposes yield-bearing assets into principal and yield components to facilitate risk transfer and price discovery in decentralized finance (DeFi). We propose a model that characterizes yield token dynamics using stochastic differential equations. We derive a no-arbitrage pricing framework for yield tokens, enabling their use in hedging future yield volatility and managing interest rate risk in decentralized l…

Det här är samma grejer som Fredrik Nyström har kört med i flera år. https://youtu.be/0Fvn5QiMsOo
Det finns en ökad risk för flimmer hos de som tränar mycket, framför allt konditionsidrottare. Det innebär inte att det är en dålig idé för motionärer att ställa upp i olika lopp eller träna konditio…

Agent-based Liquidity Risk Modelling for Financial Markets
Perukrishnen Vytelingum, Rory Baggott, Namid Stillman, Jianfei Zhang, Dingqiu Zhu, Tao Chen, Justin Lyon
https://arxiv.org/abs/2505.15296

Agent-based Liquidity Risk Modelling for Financial Markets
In this paper, we describe a novel agent-based approach for modelling the transaction cost of buying or selling an asset in financial markets, e.g., to liquidate a large position as a result of a margin call to meet financial obligations. The simple act of buying or selling in the market causes a price impact and there is a cost described as liquidity risk. For example, when selling a large order, there is market slippage -- each successive trade will execute at the same or worse price. When th…

The role of scalp EEG recordings during cortical visual prosthesis testing https://onlinelibrary.wiley.com/doi/10.1111/aor.15023 "Given the known risk of cortical stimulation inducing seizures", "Scalp EEG can be valuable to alert researchers to impending…

Optimizing Storytelling, Improving Audience Retention, and Reducing Waste in the Entertainment Industry
Andrew Cornfeld, Ashley Miller, Mercedes Mora-Figueroa, Kurt Samuels, Anthony Palomba
https://arxiv.org/abs/2506.00076

Optimizing Storytelling, Improving Audience Retention, and Reducing Waste in the Entertainment Industry
Television networks face high financial risk when making programming decisions, often relying on limited historical data to forecast episodic viewership. This study introduces a machine learning framework that integrates natural language processing (NLP) features from over 25000 television episodes with traditional viewership data to enhance predictive accuracy. By extracting emotional tone, cognitive complexity, and narrative structure from episode dialogue, we evaluate forecasting performance…

Asymmetry by Design: Boosting Cyber Defenders with Differential Access to AI
Shaun Ee, Chris Covino, Cara Labrador, Christina Krawec, Jam Kraprayoon, Joe O'Brien
https://arxiv.org/abs/2506.02035

Asymmetry by Design: Boosting Cyber Defenders with Differential Access to AI
As AI-enabled cyber capabilities become more advanced, we propose "differential access" as a strategy to tilt the cybersecurity balance toward defense by shaping access to these capabilities. We introduce three possible approaches that form a continuum, becoming progressively more restrictive for higher-risk capabilities: Promote Access, Manage Access, and Deny by Default. However, a key principle across all approaches is the need to prioritize defender access, even in the most restrictive scen…

Good Morning #Canada
It's National Rotisserie Chicken Day, which means you must have a meal at #SwissChalet today or risk losing your Canadian citizenship. The first Swiss Chalet restaurant at 234 Bloor Street West in Toronto opened in 1954. It was founded by Rick Mauran, son of Maurice Mauran, the founder of the still existing Chalet BBQ of Montreal. Mauran also started Harvey's hamburger chain in 1959.
#CanadaIsAwesome #MmmmChicken
https://en.wikipedia.org/wiki/Swiss_Chalet

Minnesota Gov. Tim Walz says Democrats need to take a page from Donald Trump’s own playbook.
“Maybe it’s time for us to be a little meaner,” the former vice presidential hopeful said during a speech at the South Carolina Democratic Party’s annual convention in Columbia, South Carolina.
“Maybe it’s time for us to be a little more fierce because we have to ferociously push back on this.”
“When it’s a bully like Donald Trump, you bully the s--t out of him,” Walz added

Walz Tells Dems to ‘Bully the S**t’ Out of Trump or Risk Becoming ‘Roadkill’
The former vice presidential candidate doled out harsh words for both the president and his own party.

A General Theory of Risk Sharing
Vasily Melnikov
https://arxiv.org/abs/2505.19276 https://arxiv.org/pdf/2505.19276

A General Theory of Risk Sharing
We introduce a new paradigm for risk sharing that generalizes earlier models based on discrete agents and extends them to allow for sharing risk within a continuum of agents. Agents are represented by points of a measure space and have potentially heterogeneous risk preferences modeled by risk measures. The existence of risk minimizing allocations is proved when constrained to satisfy economically convincing conditions. In the unconstrained case, we derive the dual representation of the value f…

This https://arxiv.org/abs/2505.12583 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
Recent Foundation Model-enabled robotics (FMRs) display greatly improved general-purpose skills, enabling more adaptable automation than conventional robotics. Their ability to handle diverse tasks thus creates new opportunities to replace human labor. However, unlike general foundation models, FMRs interact with the physical world, where their actions directly affect the safety of humans and surrounding objects, requiring careful deployment and control. Based on this proposition, our survey co…

Concerning the Responsible Use of AI in the US Criminal Justice System
Cristopher Moore, Catherine Gill, Nadya Bliss, Kevin Butler, Stephanie Forrest, Daniel Lopresti, Mary Lou Maher, Helena Mentis, Shashi Shekhar, Amanda Stent, Matthew Turk
https://arxiv.org/abs/2506.00212

Concerning the Responsible Use of AI in the US Criminal Justice System
Artificial intelligence (AI) is increasingly being adopted in most industries, and for applications such as note taking and checking grammar, there is typically not a cause for concern. However, when constitutional rights are involved, as in the justice system, transparency is paramount. While AI can assist in areas such as risk assessment and forensic evidence generation, its "black box" nature raises significant questions about how decisions are made and whether they can be contested. This pa…

Residual Income Valuation and Stock Returns: Evidence from a Value-to-Price Investment Strategy
Ahmad Haboub, Aris Kartsaklas, Vasilis Sarafidis
https://arxiv.org/abs/2506.00206

Residual Income Valuation and Stock Returns: Evidence from a Value-to-Price Investment Strategy
We hypothesize that portfolio sorts based on the V/P ratio generate excess returns and consist of companies that are undervalued for prolonged periods. Results, for the US market show that high V/P portfolios outperform low V/P portfolios across horizons extending from one to three years. The V/P ratio is positively correlated to future stock returns after controlling for firm characteristics, which are well known risk proxies. Findings also indicate that profitability and investment add explan…

Identifying Heart Attack Risk in Vulnerable Population: A Machine Learning Approach
Subhagata Chattopadhyay, Amit K Chattopadhyay
https://arxiv.org/abs/2505.21139

Identifying Heart Attack Risk in Vulnerable Population: A Machine Learning Approach
The COVID-19 pandemic has significantly increased the incidence of post-infection cardiovascular events, particularly myocardial infarction, in individuals over 40. While the underlying mechanisms remain elusive, this study employs a hybrid machine learning approach to analyze epidemiological data in assessing 13 key heart attack risk factors and their susceptibility. Based on a unique dataset that combines demographic, biochemical, ECG, and thallium stress-tests, this study categorizes distinc…

Political turmoil in Washington has dried up job opportunities in what Professor Ladher calls
“the best research ecosystem in the world.”
Some decided they would now rather take their skills elsewhere, including Austria, Japan and Australia,
while others opted to stay in India.
As the Trump administration moves with abandon to deny visas,
expel foreign students and slash spending on research,
scientists in the United States are becoming increasingly alarm…

World Scientists Look Elsewhere as U.S. Labs Stagger Under Trump Cuts
With the welcome mat withdrawn for promising researchers from around the world, America is at risk of losing its longstanding pre-eminence in the sciences.

This https://arxiv.org/abs/2411.16746 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

LoBAM: LoRA-Based Backdoor Attack on Model Merging
Model merging is an emerging technique that integrates multiple models fine-tuned on different tasks to create a versatile model that excels in multiple domains. This scheme, in the meantime, may open up backdoor attack opportunities where one single malicious model can jeopardize the integrity of the merged model. Existing works try to demonstrate the risk of such attacks by assuming substantial computational resources, focusing on cases where the attacker can fully fine-tune the pre-trained m…

Bayesian Inference for Spatially-Temporally Misaligned Data Using Predictive Stacking
Soumyakanti Pan, Sudipto Banerjee
https://arxiv.org/abs/2505.24397 ht…

Bayesian Inference for Spatially-Temporally Misaligned Data Using Predictive Stacking
Air pollution remains a major environmental risk factor that is often associated with adverse health outcomes. However, quantifying and evaluating its effects on human health is challenging due to the complex nature of exposure data. Recent technological advances have led to the collection of various indicators of air pollution at increasingly high spatial-temporal resolutions (e.g., daily averages of pollutant levels at spatial locations referenced by latitude-longitude). However, health outco…

Self-driving technologies need the help of the public: A narrative review of the evidence
Jonathan Smith, Siddartha Khastgir
https://arxiv.org/abs/2505.23472

Self-driving technologies need the help of the public: A narrative review of the evidence
If public trust is lot in a new technology early in its life cycle it can take much more time for the benefits of that technology to be realised. Eventually tens-of-millions of people will collectively have the power to determine self-driving technology success of failure driven by their perception of risk, data handling, safety, governance, accountability, benefits to their life and more. This paper reviews the evidence on safety critical technology covering trust, engagement, and acceptance. …

Watermarking Without Standards Is Not AI Governance
Alexander Nemecek, Yuzhou Jiang, Erman Ayday
https://arxiv.org/abs/2505.23814 https://

Watermarking Without Standards Is Not AI Governance
Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This paper argues that current implementations risk serving as symbolic compliance rather than delivering effective oversight. We identify a growing gap between regulatory expectations and the technical limitations of existing watermarking schemes. Through analysis of policy proposals and industry practices, we show how incentive structures di…

[2025-06-02 Mon (UTC), no new articles found for q-fin.RM Risk Management]
#toXiv_bot_toot

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Sayyed Farid Ahamed, Sandip Roy, Soumya Banerjee, Marc Vucovich, Kevin Choi, Abdul Rahman, Alison Hu, Edward Bowen, Sachin Shetty
https://arxiv.org/abs/2505.23791

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning as a Service (MLaaS) platforms, enabling attackers to replicate confidential models by querying black-box (without internal insight) APIs. Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to such attacks. This p…

This https://arxiv.org/abs/2505.18422 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

A Task-Driven Human-AI Collaboration: When to Automate, When to Collaborate, When to Challenge
According to several empirical investigations, despite en-hancing human capabilities, human-AI cooperation fre-quently falls short of expectations and fails to reach true synergy. We propose a task-driven framework that reverses prevalent approaches by assigning AI roles according to how the task's requirements align with the capabilities of AI technology. Three major AI roles are identified through task analysis across risk and complexity dimensions: au-tonomous, assistive/collaborative, and a…

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
Baolin Zheng, Guanlin Chen, Hongqiong Zhong, Qingyang Teng, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang
https://arxiv.org/abs/2505.23793…

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models (MLLMs) have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM safety benchmarks, however, fall short in terms of data quality and coverge, and modal risk combinations, resulting in inflated and contradictory evaluation results, which hinders the discovery and governance of security concerns. Besides, we argue that vulne…

Logarithmic resilience risk metrics that address the huge variations in blackout cost
Arslan Ahmad, Ian Dobson
https://arxiv.org/abs/2505.12016 https://

Logarithmic resilience risk metrics that address the huge variations in blackout cost
Resilience risk metrics must address the customer cost of the largest blackouts of greatest impact. However, there are huge variations in blackout cost in observed distribution utility data that make it impractical to properly estimate the mean large blackout cost and the corresponding risk. These problems are caused by the heavy tail observed in the distribution of customer costs. To solve these problems, we propose resilience metrics that describe large blackout risk using the mean of the log…

This https://arxiv.org/abs/2502.14479 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Modelling the term-structure of default risk under IFRS 9 within a multistate regression framework
The lifetime behaviour of loans is notoriously difficult to model, which can compromise a bank's financial reserves against future losses, if modelled poorly. Therefore, we present a data-driven comparative study amongst three techniques in modelling a series of default risk estimates over the lifetime of each loan, i.e., its term-structure. The behaviour of loans can be described using a nonstationary and time-dependent semi-Markov model, though we model its elements using a multistate regress…