Tootfinder

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/5]:
- Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Sheshadri, Ewart, Guo, Lynch, Wu, Hebbar, Sleight, Stickland, Perez, Hadfield-Menell, Casper

Esta malta que diz que Portugal é um estado aliado dos Estados Unidos tem olhado para o que se estš a passar no mundo no ultimo ano, ou tem estado a dormir?
A NATO estš morta, rapazes. Metam isso na cabeça. Pode ser que dela saia uma aliança centrada na Europa, eventualmente com participação de outros estados (Canadš, e tal), mas os EUA são adversšrios, não aliados. Com potencial para se tornarem mesmo inimigos.
Só falta mesmo formalizar o que jš acontece na realidade.

Attractive and Repulsive Perceptual Biases Naturally Emerge in Generative Adversarial Inference
Hyun-Jun Jeon, Hansol Choi, Oh-Sang Kwon
https://arxiv.org/abs/2507.19944 https:/…

Attractive and Repulsive Perceptual Biases Naturally Emerge in Generative Adversarial Inference
Human perceptual estimates exhibit a striking reversal in bias depending on uncertainty: they shift toward prior expectations under high sensory uncertainty, but away from them when internal noise is dominant. While Bayesian inference combined with efficient coding can explain this dual bias, existing models rely on handcrafted priors or fixed encoders, offering no account of how such representations and inferences could emerge through learning. We introduce a Generative Adversarial Inference (…

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
Mengmeng Li, Philipp Schneider, Jelisaveta Aleksi\'c, Daniel Kuhn
https://arxiv.org/abs/2508.18768

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $\widetilde{\mathcal{O}}(\sqrt{T})$ regret in the adversarial regime and $\widetilde{\mathcal{O}}(\ln T)$ regret in the corrupted stochastic regime. Our approach builds on the Follow-the-Regularized-Leader (FTRL) framework equipped with a Shannon entropy regularizer, yielding a flexible method that admits efficient implementations. Beyond regret bounds, we tackle the pra…

A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs
Anders M{\o}lmen H{\o}st, Pierre Lison, Leon Moonen
https://arxiv.org/abs/2508.18439 http…

A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs
Vulnerability databases, such as the National Vulnerability Database (NVD), offer detailed descriptions of Common Vulnerabilities and Exposures (CVEs), but often lack information on their real-world impact, such as the tactics, techniques, and procedures (TTPs) that adversaries may use to exploit the vulnerability. However, manually linking CVEs to their corresponding TTPs is a challenging and time-consuming task, and the high volume of new vulnerabilities published annually makes automated sup…

Isso é muito sério: #ElonMusk interfere ativamente em #política e #guerra
#bigtechs
@…

Two-Level Priority Coding for Resilience to Arbitrary Blockage Patterns
Mine Gokce Dogan, Abhiram Kadiyala, Jaimin Shah, Martina Cardone, Christina Fragouli
https://arxiv.org/abs/2508.16899

Two-Level Priority Coding for Resilience to Arbitrary Blockage Patterns
Ultra-reliable low-latency communication is essential in mission-critical settings, including military applications, where persistent and asymmetric link blockages caused by mobility, jamming, or adversarial attacks can disrupt delay-sensitive transmissions. This paper addresses this challenge by deploying a multilevel diversity coding (MDC) scheme that controls the received information, offers distinct reliability guarantees based on the priority of data streams, and maintains low design and o…

Risk-Averse and Optimistic Advertiser Incentive Compatibility in Auto-bidding
Christopher Liaw, Wennan Zhu
https://arxiv.org/abs/2508.16823 https://arxiv.o…

Risk-Averse and Optimistic Advertiser Incentive Compatibility in Auto-bidding
The rise of auto-bidding has created challenges for ensuring advertiser incentive compatibility, particularly when advertisers delegate bidding to agents with high-level constraints. One challenge in defining incentive compatibility is the multiplicity of equilibria. After advertisers submit reports, it is unclear what the result will be and one only has knowledge of a range of possible results. Nevertheless, Alimohammadi et al. proposed a notion of Auto-bidding Incentive Compatibility (AIC) wh…

Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
Adithya Mohan, Dominik R\"o{\ss}le, Daniel Cremers, Torsten Sch\"on
https://arxiv.org/abs/2507.17070

Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
Recent advancements in Deep Reinforcement Learning (DRL) have demonstrated its applicability across various domains, including robotics, healthcare, energy optimization, and autonomous driving. However, a critical question remains: How robust are DRL models when exposed to adversarial attacks? While existing defense mechanisms such as adversarial training and distillation enhance the resilience of DRL models, there remains a significant research gap regarding the integration of multiple defense…

Network Structures as an Attack Surface: Topology-Based Privacy Leakage in Federated Learning
Murtaza Rangwala, Richard O. Sinnott, Rajkumar Buyya
https://arxiv.org/abs/2506.19260

Network Structures as an Attack Surface: Topology-Based Privacy Leakage in Federated Learning
Federated learning systems increasingly rely on diverse network topologies to address scalability and organizational constraints. While existing privacy research focuses on gradient-based attacks, the privacy implications of network topology knowledge remain critically understudied. We conduct the first comprehensive analysis of topology-based privacy leakage across realistic adversarial knowledge scenarios, demonstrating that adversaries with varying degrees of structural knowledge can infer s…