Tootfinder

Utilizing AI for Aviation Post-Accident Analysis Classification
Aziida Nanyonga, Graham Wild
https://arxiv.org/abs/2506.00169 https://

Utilizing AI for Aviation Post-Accident Analysis Classification
The volume of textual data available in aviation safety reports presents a challenge for timely and accurate analysis. This paper examines how Artificial Intelligence (AI) and, specifically, Natural Language Processing (NLP) can automate the process of extracting valuable insights from this data, ultimately enhancing aviation safety. The paper reviews ongoing efforts focused on the application of NLP and deep learning to aviation safety reports, with the goal of classifying the level of damage …

Newark’s radar fiasco has been making headlines, and there was a wave of alarming incidents early in 2025 — but what’s the larger picture of air safety in the US right now?
Do we have good data on whether there have been more incidents or near misses across the country this year on an ongoing basis?

E-scooter injury toll revealed in study just ‘tip of the iceberg’ in Australia, doctors warn | Road safety | The Guardian
https://www.theguardian.com/world/2025/jun/04/e-scooter-injury-toll-reve…

This https://arxiv.org/abs/2505.17072 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies generally fail to offer actionable solutions beyond data augmentation for achieving more robust safety mechanisms. This paper identifies a fundamental cause of this superficiality: existing alignment approaches often presume that models can implicitly learn a …

RewardBench 2: Advancing Reward Model Evaluation
Saumya Malik, Valentina Pyatkin, Sander Land, Jacob Morrison, Noah A. Smith, Hannaneh Hajishirzi, Nathan Lambert
https://arxiv.org/abs/2506.01937

RewardBench 2: Advancing Reward Model Evaluation
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains. The community has begun establishing best practices for evaluating reward models, from the development of benchmarks that test capabilities in specific skill areas to others that test agreement with human preferences. At the same time, progress in evaluation has not…

DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving
Dawood Wasif, Terrence J Moore, Chandan K Reddy, Jin-Hee Cho
https://arxiv.org/abs/2506.00819

DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving
End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vision-language-guided reinforcement learning (RL) methods introduce semantic feedback, they often rely on static prompts and fixed objectives, limiting adaptability to dynamic driving scenes. We present DriveMind, a unified semantic reward framework that integrates: (i) a contrastive Vision-Language Model (VLM) encoder…

This https://arxiv.org/abs/2503.05728 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Political Neutrality in AI Is Impossible- But Here Is How to Approximate It
AI systems often exhibit political bias, influencing users' opinions and decisions. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for fairness and safety, this position paper argues that true political neutrality is neither feasible nor universally desirable due to its subjective nature and the biases inherent in AI training data, algorithms, and user interactions. However, inspired by Joseph Raz's philosophical insight that "neutrality [...] can b…

AI-Driven Vehicle Condition Monitoring with Cell-Aware Edge Service Migration
Charalampos Kalalas, Pavol Mulinka, Guillermo Candela Belmonte, Miguel Fornell, Michail Dalgitsis, Francisco Paredes Vera, Javier Santaella S\'anchez, Carmen Vicente Villares, Roshan Sedar, Eftychia Datsika, Angelos Antonopoulos, Antonio Fern\'andez Ojea, Miquel Payaro

AI-Driven Vehicle Condition Monitoring with Cell-Aware Edge Service Migration
Artificial intelligence (AI) has been increasingly applied to the condition monitoring of vehicular equipment, aiming to enhance maintenance strategies, reduce costs, and improve safety. Leveraging the edge computing paradigm, AI-based condition monitoring systems process vast streams of vehicular data to detect anomalies and optimize operational performance. In this work, we introduce a novel vehicle condition monitoring service that enables real-time diagnostics of a diverse set of anomalies …

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…

Automated Vehicles Should be Connected with Natural Language
Xiangbo Gao, Keshu Wu, Hao Zhang, Kexin Tian, Yang Zhou, Zhengzhong Tu
https://arxiv.org/abs/2507.01059

Automated Vehicles Should be Connected with Natural Language
Multi-agent collaborative driving promises improvements in traffic safety and efficiency through collective perception and decision making. However, existing communication media -- including raw sensor data, neural network features, and perception results -- suffer limitations in bandwidth efficiency, information completeness, and agent interoperability. Moreover, traditional approaches have largely ignored decision-level fusion, neglecting critical dimensions of collaborative driving. In this …

A New Perspective On AI Safety Through Control Theory Methodologies
Lars Ullrich, Walter Zimmer, Ross Greer, Knut Graichen, Alois C. Knoll, Mohan Trivedi
https://arxiv.org/abs/2506.23703

A New Perspective On AI Safety Through Control Theory Methodologies
While artificial intelligence (AI) is advancing rapidly and mastering increasingly complex problems with astonishing performance, the safety assurance of such systems is a major concern. Particularly in the context of safety-critical, real-world cyber-physical systems, AI promises to achieve a new level of autonomy but is hampered by a lack of safety assurance. While data-driven control takes up recent developments in AI to improve control systems, control theory in general could be leveraged t…

Two related news stories that hint of the destruction of US assets and infrastructure that are critical to the safety of all of us:
"Severe weather hits the US hard as key forecast offices reel from Trump cuts"
"Trump delays plan to cut satellite data access crucial to hurricane forecasting"

Improving Multi-Vehicle Perception Fusion with Millimeter-Wave Radar Assistance
Zhiqing Luo, Yi Wang, Yingying He, Wei Wang
https://arxiv.org/abs/2506.00837

Improving Multi-Vehicle Perception Fusion with Millimeter-Wave Radar Assistance
Cooperative perception enables vehicles to share sensor readings and has become a new paradigm to improve driving safety, where the key enabling technology for realizing this vision is to real-time and accurately align and fuse the perceptions. Recent advances to align the views rely on high-density LiDAR data or fine-grained image feature representations, which however fail to meet the requirements of accuracy, real-time, and adaptability for autonomous driving. To this end, we present MMatch,…

A Comprehensive Review of Human Error in Risk-Informed Decision Making: Integrating Human Reliability Assessment, Artificial Intelligence, and Human Performance Models
Xingyu Xiao, Hongxu Zhu, Jingang Liang, Jiejuan Tong, Haitao Wang
https://arxiv.org/abs/2507.01017

A Comprehensive Review of Human Error in Risk-Informed Decision Making: Integrating Human Reliability Assessment, Artificial Intelligence, and Human Performance Models
Human error remains a dominant risk driver in safety-critical sectors such as nuclear power, aviation, and healthcare, where seemingly minor mistakes can cascade into catastrophic outcomes. Although decades of research have produced a rich repertoire of mitigation techniques, persistent limitations: scarce high-quality data, algorithmic opacity, and residual reliance on expert judgment, continue to constrain progress. This review synthesizes recent advances at the intersection of risk-informed …

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
Shuang Ao, Yi Dong, Jinwei Hu, Sarvapali Ramchurn
https://arxiv.org/abs/2506.18931

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to harmful outputs. Existing safety alignment methods struggle to capture complex parameter shifts, leading to suboptimal safety-utility trade-offs. To address this issue, we propose Safe Pruning LoRA (SPLoRA), a novel pruning-based approach that selectively remove…

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks
Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Gaosheng Zhao, Dusit Niyato, Geng Sun, Shiwen Mao, Dong In Kim
https://arxiv.org/abs/2506.00417

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks
World models are emerging as a transformative paradigm in artificial intelligence, enabling agents to construct internal representations of their environments for predictive reasoning, planning, and decision-making. By learning latent dynamics, world models provide a sample-efficient framework that is especially valuable in data-constrained or safety-critical scenarios. In this paper, we present a comprehensive overview of world models, highlighting their architecture, training paradigms, and a…

Automated Formal Verification of Area-Optimized Safety Registers in Automotive SoCs
Shuhang Zhang, Bryan Olmos
https://arxiv.org/abs/2505.17990 https://

Automated Formal Verification of Area-Optimized Safety Registers in Automotive SoCs
Registers are primary storage elements in System-on-chip~(SoC) designs and play an important role in maintaining state information and processing data in digital systems. With respect to the ISO26262 standard, these registers require high levels of reliability and fault tolerance. For this reason, safety-critical applications require that normal registers are equipped with additional safety components to construct safety registers, which ensure system stability and fault tolerance. However, the…

RealDrive: Retrieval-Augmented Driving with Diffusion Models
Wenhao Ding, Sushant Veer, Yuxiao Chen, Yulong Cao, Chaowei Xiao, Marco Pavone
https://arxiv.org/abs/2505.24808

RealDrive: Retrieval-Augmented Driving with Diffusion Models
Learning-based planners generate natural human-like driving behaviors by learning to reason about nuanced interactions from data, overcoming the rigid behaviors that arise from rule-based planners. Nonetheless, data-driven approaches often struggle with rare, safety-critical scenarios and offer limited controllability over the generated trajectories. To address these challenges, we propose RealDrive, a Retrieval-Augmented Generation (RAG) framework that initializes a diffusion-based planning po…

This https://arxiv.org/abs/2301.06136 has been replaced.
link: https://scholar.google.com/scholar?q=a

Quantitative Verification with Neural Networks
We present a data-driven approach to the quantitative verification of probabilistic programs and stochastic dynamical models. Our approach leverages neural networks to compute tight and sound bounds for the probability that a stochastic process hits a target condition within finite time. This problem subsumes a variety of quantitative verification questions, from the reachability and safety analysis of discrete-time stochastic dynamical models, to the study of assertion-violation and terminatio…

Waymo applied for a NYC permit to test its cars with safety drivers and plans to start collecting mapping data with manually driven cars in Manhattan in July (Andrew J. Hawkins/The Verge)
https://www.theverge.com/news/689093/waymo-nyc-permit…

Waymo’s robotaxis are coming back to New York City
Waymo applied for a permit to test autonomous vehicles with safety drivers in New York City. And it hopes it can change the state law to allow it to operate fully driverless.

Assessing the Influence of Pavement Performance on Road Safety Through Crash Frequency and Severity Analysis
Prathyush Kumar Reddy Lebaku, Lu Gao, Jingran Sun, Xingju Wang, Xuejian Kang
https://arxiv.org/abs/2506.16485

Assessing the Influence of Pavement Performance on Road Safety Through Crash Frequency and Severity Analysis
Road safety is impacted by a range of factors that can be categorized into human, vehicle, and roadway/environmental elements. This research explores the connection between pavement performance and road safety, particularly in relation to crash frequency and severity, using data from the Iowa Department of Transportation (DOT) for 2022. By merging crash data with pavement inventory data, we conduct a spatial analysis that incorporates the geographical coordinates of crash sites with the conditi…

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
Christoph Schnabl, Daniel Hugenroth, Bill Marino, Alastair R. Beresford
https://arxiv.org/abs/2506.23706

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits, which run inside Trusted Execution Environments and enable users to verify interaction with a compliant AI model. Our work protects sensitive data even when model provider and auditor do not trust each other. This addresses verification challenges raised in re…

Annual DC Privacy Forum: Convening Top Voices in Governance in the Digital Age
https://fpf.org/blog/annual-dc-privacy-forum-convening-top-voices-in-governance-in-the-digital-age/
@…

Dorothea Baur reflecting on #AI tech bros going all in on even your most personal data. Claiming to help you solve a problem which they helped create in the beginning:
"A breach of trust enabled by AI now becomes the justification for surveillance-based trust systems. And the very people who helped break the system are offering to fix it – in exchange for your iris. That’s not a safety fe…

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. …

Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
Haoming Jing, Yorie Nakahira
https://arxiv.org/abs/2506.17927 https://…

Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
Many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data. However, existing control techniques often assume access to complete dynamics or perfect simulators with fully observable states, which are necessary to verify whether the system remains within a safe set (forward invariance) or safe actions are consistently feasible at all times. To address this limitation, we propose a…

Never a let-up in cybersecurity developments, so don't miss today's Metacurity for the most critical infosec developments you should know, including
--US grocery distributor United Natural Foods is the latest retail-related cyber victim
--M&S reopens website to shoppers,
--Google account phone numbers could have been brute-forced,
--TX and IL warn of breach-related data exposure,
--NHS blood supply still short a year after ransomware attack,
--C…

US grocery distributor United Natural Foods is the latest retail-related cyber victim
M&S reopens website to shoppers, Google account phone numbers could have been brute-forced, TX and IL warn of breach-related data exposure, NHS blood supply still short a year after ransomware attack, Comcast and Digital Realty were Salt Typhoon victims, Ofcom probes 4chan safety, much more

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
Kathleen C. Fraser, Hillary Dawkins, Isar Nejadgholi, Svetlana Kiritchenko
https://arxiv.org/abs/2506.17209

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the fine-tuning data does not contain any harmful content. We consider this to be a critical failure mode of LLMs due to the widespread uptake of fine-tuning, combined with the benign nature of the "attack". Most well-intentioned developers are likely unaware that th…

UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data
Vasiliki Balaska, Ioannis Tsampikos Papapetros, Katerina Maria Oikonomou, Loukas Bampis, Antonios Gasteratos
https://arxiv.org/abs/2506.13505

UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data
The mining sector increasingly adopts digital tools to improve operational efficiency, safety, and data-driven decision-making. One of the key challenges remains the reliable acquisition of high-resolution, geo-referenced spatial information to support core activities such as extraction planning and on-site monitoring. This work presents an integrated system architecture that combines UAV-based sensing, LiDAR terrain modeling, and deep learning-based object detection to generate spatially accur…

Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats
Utku Demir, Yalin E. Sagduyu, Tugba Erpek, Hossein Jafari, Sastry Kompella, Mengran Xue
https://arxiv.org/abs/2505.23706

Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats
In connected and autonomous vehicles, machine learning for safety message classification has become critical for detecting malicious or anomalous behavior. However, conventional approaches that rely on centralized data collection or purely local training face limitations due to the large scale, high mobility, and heterogeneous data distributions inherent in inter-vehicle networks. To overcome these challenges, this paper explores Distributed Federated Learning (DFL), whereby vehicles collaborat…

Safety-Driven Response Adaptive Randomisation: An Application in Non-inferiority Oncology Trials
Maria Vittoria Chiaruttini, Lukas Pin, Sofia S. Villar
https://arxiv.org/abs/2506.08864

Safety-Driven Response Adaptive Randomisation: An Application in Non-inferiority Oncology Trials
The majority of response-adaptive randomisation (RAR) designs in the literature use efficacy data to dynamically allocate patients. Their applicability in settings where the efficacy measure is observable with a random delay, such as overall survival, remains challenging. This paper introduces a RAR design referred to as SAFER (Safety-Aware Flexible Elastic Randomisation) design, which uses early-emerging safety data to inform treatment allocation decisions in oncology trials. However, the desi…

Understanding and Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding
Youze Wang, Zijun Chen, Ruoyu Chen, Shishen Gu, Yinpeng Dong, Hang Su, Jun Zhu, Meng Wang, Richang Hong, Wenbo Hu
https://arxiv.org/abs/2506.12336

Understanding and Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding
Recent advancements in multimodal large language models for video understanding (videoLLMs) have improved their ability to process dynamic multimodal data. However, trustworthiness challenges factual inaccuracies, harmful content, biases, hallucinations, and privacy risks, undermine reliability due to video data's spatiotemporal complexities. This study introduces Trust-videoLLMs, a comprehensive benchmark evaluating videoLLMs across five dimensions: truthfulness, safety, robustness, fairness, …

Data-Centric Safety and Ethical Measures for Data and AI Governance
Srija Chakraborty
https://arxiv.org/abs/2506.10217 https://arxiv.…

Data-Centric Safety and Ethical Measures for Data and AI Governance
Datasets play a key role in imparting advanced capabilities to artificial intelligence (AI) foundation models that can be adapted to various downstream tasks. These downstream applications can introduce both beneficial and harmful capabilities -- resulting in dual use AI foundation models, with various technical and regulatory approaches to monitor and manage these risks. However, despite the crucial role of datasets, responsible dataset design and ensuring data-centric safety and ethical pract…

On Continuous Monitoring of Risk Violations under Unknown Shift
Alexander Timans, Rajeev Verma, Eric Nalisnick, Christian A. Naesseth
https://arxiv.org/abs/2506.16416

On Continuous Monitoring of Risk Violations under Unknown Shift
Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assurances on the system's risk established beforehand. Common risk control frameworks rely on fixed assumptions and lack mechanisms to continuously monitor deployment reliability. In this work, we propose a general framework for the real-time monitoring of risk violations in evolving data streams. Leveraging the 'testing …

Regression Testing Optimization for ROS-based Autonomous Systems: A Comprehensive Review of Techniques
Yupeng Jiang, Shuaiyi Sun, Xi Zheng
https://arxiv.org/abs/2506.16101

Regression Testing Optimization for ROS-based Autonomous Systems: A Comprehensive Review of Techniques
Regression testing plays a critical role in maintaining software reliability, particularly for ROS-based autonomous systems (ROSAS), which frequently undergo continuous integration and iterative development. However, conventional regression testing techniques face significant challenges when applied to autonomous systems due to their dynamic and non-deterministic behaviors, complex multi-modal sensor data, asynchronous distributed architectures, and stringent safety and real-time constraints. A…

Once again: #FuckEricAdams
Unbelievable how he's managed to avoid jailtime breaking federal/state laws while City Council allows him to continue to break _their_laws as well.

https://…

No to 15 mph e-bike speed limit, yes to real safety! - Transportation Alternatives
A ridiculous 15 mph speed limit for e-bikes won't work. Tell Mayor Adams and City Council: We need effective, data-driven policies that protect everyone, and accountability for the corporations fueling chaos on our streets — not the cyclists surviving it.

Statistical Guarantees in Data-Driven Nonlinear Control: Conformal Robustness for Stability and Safety
Ting-Wei Hsu, Hiroyasu Tsukamoto
https://arxiv.org/abs/2506.06228

Statistical Guarantees in Data-Driven Nonlinear Control: Conformal Robustness for Stability and Safety
We present a true-dynamics-agnostic, statistically rigorous framework for establishing exponential stability and safety guarantees of closed-loop, data-driven nonlinear control. Central to our approach is the novel concept of conformal robustness, which robustifies the Lyapunov and zeroing barrier certificates of data-driven dynamical systems against model prediction uncertainties using conformal prediction. It quantifies these uncertainties by leveraging rank statistics of prediction scores ov…

This https://arxiv.org/abs/2505.17132 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Robustifying Vision-Language Models via Dynamic Token Reweighting
Large vision-language models (VLMs) are highly vulnerable to jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates multimodal jailbreak attacks through optimizing the model's key-value (KV) caches. Rather than relying on curated safety-specific data or costly image-to-text conversion, we introduce a new formulation of the safety-relevant distributional shift induced by the visual modal…

Enhancing Evacuation Safety: Detecting Post-Nuclear Event Radiation Levels in an Urban Area
Ellis Duncalfe, Milena Radenkovic
https://arxiv.org/abs/2506.19044

Enhancing Evacuation Safety: Detecting Post-Nuclear Event Radiation Levels in an Urban Area
The detonation of an improvised nuclear device (IND) in an urban area would cause catastrophic damage, followed by hazardous radioactive fallout. Timely dissemination of radiation data is crucial for evacuation and casualty reduction. However, conventional communication infrastructure is likely to be severely disrupted. This study designs and builds a pseudorealistic, geospatially and temporally dynamic post-nuclear event (PNE) scenario using the Opportunistic Network Environment (ONE) simulato…

A data-driven analysis of the impact of non-compliant individuals on epidemic diffusion in urban settings
Fabio Mazza, Marco Brambilla, Carlo Piccardi, Francesco Pierri
https://arxiv.org/abs/2506.13325

A data-driven analysis of the impact of non-compliant individuals on epidemic diffusion in urban settings
Individuals who do not comply with public health safety measures pose a significant challenge to effective epidemic control, as their risky behaviours can undermine public health interventions. This is particularly relevant in urban environments because of their high population density and complex social interactions. In this study, we employ detailed contact networks, built using a data-driven approach, to examine the impact of non-compliant individuals on epidemic dynamics in three major Ital…

Confidence Boosts Trust-Based Resilience in Cooperative Multi-Robot Systems
Luca Ballotta, \'Aron V\'ek\'assy, Stephanie Gil, Michal Yemini
https://arxiv.org/abs/2506.08807

Confidence Boosts Trust-Based Resilience in Cooperative Multi-Robot Systems
Wireless communication-based multi-robot systems open the door to cyberattacks that can disrupt safety and performance of collaborative robots. The physical channel supporting inter-robot communication offers an attractive opportunity to decouple the detection of malicious robots from task-relevant data exchange between legitimate robots. Yet, trustworthiness indications coming from physical channels are uncertain and must be handled with this in mind. In this paper, we propose a resilient prot…

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
Kyubyung Chae, Hyunbin Jin, Taesup Kim
https://arxiv.org/abs/2506.10020

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address this, we introduce Refusal-Aware Adaptive Injection (RAAI), a straightforward, training-free, and model-agnostic framework that repurposes LLM attack techniques. RAAI works by detecting internal refusal…

Toward Safety-First Human-Like Decision Making for Autonomous Vehicles in Time-Varying Traffic Flow
Xiao Wang, Junru Yu, Jun Huang, Qiong Wu, Ljubo Vacic, Changyin Sun
https://arxiv.org/abs/2506.14502

Toward Safety-First Human-Like Decision Making for Autonomous Vehicles in Time-Varying Traffic Flow
Despite the recent advancements in artificial intelligence technologies have shown great potential in improving transport efficiency and safety, autonomous vehicles(AVs) still face great challenge of driving in time-varying traffic flow, especially in dense and interactive situations. Meanwhile, human have free wills and usually do not make the same decisions even situate in the exactly same scenarios, leading to the data-driven methods suffer from poor migratability and high search cost proble…

Public Perceptions of Autonomous Vehicles: A Survey of Pedestrians and Cyclists in Pittsburgh
Rudra Y. Bedekar
https://arxiv.org/abs/2506.17513 https://

Public Perceptions of Autonomous Vehicles: A Survey of Pedestrians and Cyclists in Pittsburgh
This study investigates how autonomous vehicle(AV) technology is perceived by pedestrians and bicyclists in Pittsburgh. Using survey data from over 1200 respondents, the research explores the interplay between demographics, AV interactions, infrastructural readiness, safety perceptions, and trust. Findings highlight demographic divides, infrastructure gaps, and the crucial role of communication and education in AV adoption.

Towards Data-Driven Model-Free Safety-Critical Control
Zhe Shen, Yitaek Kim, Christoffer Sloth
https://arxiv.org/abs/2506.06931 https://

Towards Data-Driven Model-Free Safety-Critical Control
This paper presents a framework for enabling safe velocity control of general robotic systems using data-driven model-free Control Barrier Functions (CBFs). Model-free CBFs rely on an exponentially stable velocity controller and a design parameter (e.g. alpha in CBFs); this design parameter depends on the exponential decay rate of the controller. However, in practice, the decay rate is often unavailable, making it non-trivial to use model-free CBFs, as it requires manual tuning for alpha. To ad…

Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
Yuxin Liu, Zhenghao Peng, Xuanhao Cui, Bolei Zhou
https://arxiv.org/abs/2506.09485

Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
Scenario-based testing is essential for validating the performance of autonomous driving (AD) systems. However, such testing is limited by the scarcity of long-tailed, safety-critical scenarios in existing datasets collected in the real world. To tackle the data issue, we propose the Adv-BMT framework, which augments real-world scenarios with diverse and realistic adversarial interactions. The core component of Adv-BMT is a bidirectional motion transformer (BMT) model to perform inverse traffic…

Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
Chunlei Li, Yilei Shi, Haoxi Hu, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou
https://arxiv.org/abs/2506.11496

Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
High-resolution computed tomography (CT) imaging is essential for medical diagnosis but requires increased radiation exposure, creating a critical trade-off between image quality and patient safety. While deep learning methods have shown promise in CT super-resolution, they face challenges with complex degradations and limited medical training data. Meanwhile, large-scale pre-trained diffusion models, particularly Stable Diffusion, have demonstrated remarkable capabilities in synthesizing fine …

Socially Aware Robot Crowd Navigation via Online Uncertainty-Driven Risk Adaptation
Zhirui Sun, Xingrong Diao, Yao Wang, Bi-Ke Zhu, Jiankun Wang
https://arxiv.org/abs/2506.14305

Socially Aware Robot Crowd Navigation via Online Uncertainty-Driven Risk Adaptation
Navigation in human-robot shared crowded environments remains challenging, as robots are expected to move efficiently while respecting human motion conventions. However, many existing approaches emphasize safety or efficiency while overlooking social awareness. This article proposes Learning-Risk Model Predictive Control (LR-MPC), a data-driven navigation algorithm that balances efficiency, safety, and social awareness. LR-MPC consists of two phases: an offline risk learning phase, where a Prob…

Sensor Fusion for Track Geometry Monitoring: Integrating On-Board Data and Degradation Models via Kalman Filtering
Huy Truong-Ba, Jacky Chin, Michael E. Cholette, Pietro Borghesani
https://arxiv.org/abs/2506.08028

Sensor Fusion for Track Geometry Monitoring: Integrating On-Board Data and Degradation Models via Kalman Filtering
Track geometry monitoring is essential for maintaining the safety and efficiency of railway operations. While Track Recording Cars (TRCs) provide accurate measurements of track geometry indicators, their limited availability and high operational costs restrict frequent monitoring across large rail networks. Recent advancements in on-board sensor systems installed on in-service trains offer a cost-effective alternative by enabling high-frequency, albeit less accurate, data collection. This study…

This https://arxiv.org/abs/2504.15585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys…

Joint Routing and Control Optimization in VANET
Chen Huang, Dingxuan Wang, Ronghui Hou
https://arxiv.org/abs/2506.08038 https://arxiv…

Joint Routing and Control Optimization in VANET
In this paper, we introduce DynaRoute, an adaptive joint optimization framework for dynamic vehicular networks that simultaneously addresses platoon control and data transmission through trajectory-aware routing and safety-constrained vehicle coordination. DynaRoute guarantees continuous vehicle movement via platoon safety control with optimizing transmission paths through real-time trajectory prediction and ensuring reliable data. Our solution achieves three key objectives: (1) maintaining pla…

Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
William F. Shen, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane
https://arxiv.org/abs/2506.14387

Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
Existing work on mitigating catastrophic forgetting in large language model (LLM) fine-tuning has primarily focused on preserving specific data or tasks, while critically overlooking the degradation of essential capabilities instilled through safety alignment, particularly the model's ability to faithfully express ignorance. In this work, we show that this capability is significantly degraded during conventional fine-tuning, leading to undesired behaviors such as hallucinations. To address this…

Enhancing Human-Robot Collaboration: A Sim2Real Domain Adaptation Algorithm for Point Cloud Segmentation in Industrial Environments
Fatemeh Mohammadi Amin, Darwin G. Caldwell, Hans Wernher van de Venn
https://arxiv.org/abs/2506.09552

Enhancing Human-Robot Collaboration: A Sim2Real Domain Adaptation Algorithm for Point Cloud Segmentation in Industrial Environments
The robust interpretation of 3D environments is crucial for human-robot collaboration (HRC) applications, where safety and operational efficiency are paramount. Semantic segmentation plays a key role in this context by enabling a precise and detailed understanding of the environment. Considering the intense data hunger for real-world industrial annotated data essential for effective semantic segmentation, this paper introduces a pioneering approach in the Sim2Real domain adaptation for semantic…

A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving
Yupeng Zhou, Can Cui, Juntong Peng, Zichong Yang, Juanwu Lu, Jitesh H Panchal, Bin Yao, Ziran Wang
https://arxiv.org/abs/2506.14100

A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving
Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale data to the safety-critical context of driving presents a significant challenge, commonly referred to as domain shift. Existing simulation-based and dataset-driven evaluation methods, although valuable, often fail to capture the full complexity of real-world …

Deep Equivariant Multi-Agent Control Barrier Functions
Nikolaos Bousias, Lars Lindemann, George Pappas
https://arxiv.org/abs/2506.07755 https://

Deep Equivariant Multi-Agent Control Barrier Functions
With multi-agent systems increasingly deployed autonomously at scale in complex environments, ensuring safety of the data-driven policies is critical. Control Barrier Functions have emerged as an effective tool for enforcing safety constraints, yet existing learning-based methods often lack in scalability, generalization and sampling efficiency as they overlook inherent geometric structures of the system. To address this gap, we introduce symmetries-infused distributed Control Barrier Functions…

Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
Yuan Gao, Mattia Piccinini, Yuchen Zhang, Dingrui Wang, Korbinian Moller, Roberto Brusnicki, Baha Zarrouki, Alessio Gambi, Jan Frederik Totz, Kai Storms, Steven Peters, Andrea Stocco, Bassam Alrifaee, Marco Pavone, Johannes Betz
https://

Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often producing limited diversity and unrealistic safety-critical cases. With the emergence of foundation models, wh…

Linguistic Ordered Weighted Averaging based deep learning pooling for fault diagnosis in a wastewater treatment plant
Alicia Beneyto-Rodriguez, Gregorio I. Sainz-Palmero, Marta Galende-Hern\'andez, Mar\'ia J. Fuente
https://arxiv.org/abs/2506.08676

Linguistic Ordered Weighted Averaging based deep learning pooling for fault diagnosis in a wastewater treatment plant
Nowadays, water reuse is a serious challenge to help address water shortages. Here, the wastewater treatment plants (WWTP) play a key role, and its proper operation is mandatory. So, fault diagnosis is a key activity for these plants. Their high complexity and large-scale require of smart methodologies for that fault diagnosis and safety operation. All these large-scale and complex industrial processes are monitored, allowing the data collection about the plant operation, so data driven approac…

Pseudo-Simulation for Autonomous Driving
Wei Cao, Marcel Hallgarten, Tianyu Li, Daniel Dauner, Xunjiang Gu, Caojun Wang, Yakov Miron, Marco Aiello, Hongyang Li, Igor Gilitschenski, Boris Ivanovic, Marco Pavone, Andreas Geiger, Kashyap Chitta
https://arxiv.org/abs/2506.04218

Pseudo-Simulation for Autonomous Driving
Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations. Real-world evaluation is often challenging due to safety concerns and a lack of reproducibility, whereas closed-loop simulation can face insufficient realism or high computational costs. Open-loop evaluation, while being efficient and data-driven, relies on metrics that generally overlook compounding errors. In this paper, we propose pseudo-simulation, a novel paradigm that addresses these limitations. Pseudo…