Tootfinder

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese, Xiao Wang, Adrian Weller, Nicolas Papernot
https://arxiv.org/abs/2505.23968

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under the guise of uncertainty. We demonstrate the practicality of this threat by introducing an uncertainty-inducing attack called Mirage, which deliberately reduces confidence in targeted input regions, th…

This https://arxiv.org/abs/2505.19521 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures
Learning unknown dynamics under environmental (or external) constraints is fundamental to many fields (e.g., modern robotics), particularly challenging when constraint information is only locally available and uncertain. Existing approaches requiring global constraints or using probabilistic filtering fail to fully exploit the geometric structure inherent in local measurements (by using, e.g., sensors) and constraints. This paper presents a geometric framework unifying measurements, constraints…

This https://arxiv.org/abs/2412.16772 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?
The ongoing revolution in language modeling has led to various novel applications, some of which rely on the emerging social abilities of large language models (LLMs). Already, many turn to the new cyber friends for advice during the pivotal moments of their lives and trust them with the deepest secrets, implying that accurate shaping of the LLM's personality is paramount. To this end, state-of-the-art approaches exploit a vast variety of training data, and prompt the model to adopt a particula…

This https://arxiv.org/abs/2502.17982 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Kinetic variable-sample methods for stochastic optimization problems
We discuss kinetic-based particle optimization methods and variable-sample strategies for problems where the cost function represents the expected value of a random mapping. Kinetic-based optimization methods rely on a consensus mechanism targeting the global minimizer, and they exploit tools of kinetic theory to establish a rigorous framework for proving convergence to that minimizer. Variable-sample strategies replace the expected value by an approximation at each iteration of the optimizatio…

Deception in Oligopoly Games via Adaptive Nash Seeking Systems
Michael Tang, Miroslav Krstic, Jorge Poveda
https://arxiv.org/abs/2505.24112 https://…

Deception in Oligopoly Games via Adaptive Nash Seeking Systems
In the theory of multi-agent systems, deception refers to the strategic manipulation of information to influence the behavior of other agents, ultimately altering the long-term dynamics of the entire system. Recently, this concept has been examined in the context of model-free Nash equilibrium seeking (NES) algorithms for noncooperative games. Specifically, it was demonstrated that players can exploit knowledge of other players' exploration signals to drive the system toward a ``deceptive" Nash…

This https://arxiv.org/abs/2501.10639 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
Ensuring safety alignment has become a critical requirement for large language models (LLMs), particularly given their widespread deployment in real-world applications. However, LLMs remain susceptible to jailbreak attacks, which exploit system vulnerabilities to bypass safety measures and generate harmful outputs. Although numerous defense mechanisms based on adversarial training have been proposed, a persistent challenge lies in the exacerbation of over-refusal behaviors, which compromise the…

China-linked hackers exploit Google Calendar in cyberattacks on governments https://therecord.media/china-linked-apt41-exploits-google-calendar-in-cyberattacks

This https://arxiv.org/abs/2502.20770 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGT_…

Learning to Steer Learners in Games
We consider the problem of learning to exploit learning algorithms through repeated interactions in games. Specifically, we focus on the case of repeated two player, finite-action games, in which an optimizer aims to steer a no-regret learner to a Stackelberg equilibrium without knowledge of its payoffs. We first show that this is impossible if the optimizer only knows that the learner is using an algorithm from the general class of no-regret algorithms. This suggests that the optimizer require…

Refining Datapath for Microscaling ViTs
Can Xiao, Jianyi Cheng, Aaron Zhao
https://arxiv.org/abs/2505.22194 https://arxiv.org/pdf/250…

Refining Datapath for Microscaling ViTs
Vision Transformers (ViTs) leverage the transformer architecture to effectively capture global context, demonstrating strong performance in computer vision tasks. A major challenge in ViT hardware acceleration is that the model family contains complex arithmetic operations that are sensitive to model accuracy, such as the Softmax and LayerNorm operations, which cannot be mapped onto efficient hardware with low precision. Existing methods only exploit parallelism in the matrix multiplication ope…

Learned Adaptive Mesh Generation
Zhiyuan Zhang, Amir Vaxman, Stefanos-Aldo Papanicolopulos, Kartic Subr
https://arxiv.org/abs/2505.20457 https://

Learned Adaptive Mesh Generation
The distribution and evolution of several real-world quantities, such as temperature, pressure, light, and heat, are modelled mathematically using Partial Differential Equations (PDEs). Solving PDEs defined on arbitrary 3D domains, say a 3D scan of a turbine's blade, is computationally expensive and scales quadratically with discretization. Traditional workflows in research and industry exploit variants of the finite element method (FEM), but some key benefits of using Monte Carlo (MC) methods …

Now that most services have implemented 2FA (multi-factor authentication) we are seeing a new breed of scams that exploit them and trick people into approving requests under the guise of fraud prevention, which is easy to do now that we are bombarded by more secure logins. The next time you get a fraud prevention alert, be quadruple vigilant about how you respond to 2FA requests.

I've seen outrage expressed at this one percent decrease of the lowest marginal tax rate as "not being a 'middle-class tax cut' since everyone -- billionaires included -- will benefit from it."
It's true; it means that anyone making more than $57,375 will pay 1% less on that first $57K. So, yes, a billionaire and I will both pay $573.75 less. That's how tax brackets work.
It's bad enough that some people don't understand taxation; it's worse that others exploit that to foment outrage.

US 11.04.2025
"Justice Department Implements Critical National Security Program to Protect Americans’ Sensitive Data from Foreign Adversaries"
https://www.justice.gov/opa/pr/justice-department-implements-…

Now that most services have implemented 2FA (multi-factor authentication) we are seeing a new breed of scams that exploit them and trick people into approving requests under the guise of fraud prevention, which is easy to do now that we are bombarded by more secure logins. The next time you get a fraud prevention alert, be quadruple vigilant about how you respond to 2FA requests.

This https://arxiv.org/abs/2406.06095 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMS_…

An extension of C++ with memory-centric specifications for HPC to reduce memory footprints and streamline MPI development
The C++ programming language and its cousins lean towards a memory-inefficient storage of structs: The compiler inserts helper bits such that individual instance variables fit to byte or cache boundaries, while it is not able to exploit knowledge about the range of integers, enums or bitsets. Furthermore, the language provides neither support for data exchange via MPI nor for arbitrary floating-point precisions. We propose C++ attributes through which developers can guide the compiler what memo…