AI Safety & Ethics

AI is going to be bad for security in the short-term, but much better than humans in the long-term.

arXiv:2603.28787v1 Announce Type: cross Abstract: Traditional liquid identification instruments are often unavailable to the general public. This paper shows th

arXiv:2603.28798v1 Announce Type: cross Abstract: Physically Unclonable Functions (PUFs) provide promising hardware security for IoT authentication, leveraging

arXiv:2603.28824v1 Announce Type: cross Abstract: Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of

arXiv:2603.29062v1 Announce Type: cross Abstract: LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve

arXiv:2603.29759v1 Announce Type: cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards a

Discovered by FutureSearch researcher Callum McMahon, a supply chain attack against LiteLLM on PyPI resulted in over 40 thousand downloads of a compromised vers

Regulatory AI sandboxes are gaining popularity. Here's what they are, plus their tradeoffs. An AI Insider scoop.

arXiv:2603.26676v1 Announce Type: cross Abstract: Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming.

arXiv:2603.26712v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) is increasingly used to write and refactor research code, expanding co

arXiv:2603.26725v1 Announce Type: cross Abstract: We prove that capability safety admits an exact representation as propositional Datalog evaluation (Datalogpro

arXiv:2603.27117v1 Announce Type: cross Abstract: This paper investigates how gender shapes privacy decision-making in youth smart voice assistant (SVA) ecosyst

arXiv:2603.27747v1 Announce Type: cross Abstract: Recently, crowd-sourced online criminal investigations have used generative-AI to enhance low-quality visual e

arXiv:2603.28594v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) achieve strong performance in semantic segmentation for robotic perception but rem

arXiv:2603.28650v1 Announce Type: cross Abstract: Can a safety gate permit unbounded beneficial self-modification while maintaining bounded cumulative risk? We

arXiv:2603.28675v1 Announce Type: cross Abstract: Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithm

arXiv:2504.11967v4 Announce Type: replace-cross Abstract: Unmanned Aerial Vehicles (UAVs) are indispensable for infrastructure inspection, surveillance, and rel

arXiv:2505.13280v2 Announce Type: replace-cross Abstract: Despite significant advances in the area, adversarial robustness remains a critical challenge in syste

Comments

The US senator said on Tuesday that a moratorium would give lawmakers time to "ensure that AI is safe." Alexandria Ocasio-Cortez will introduce a similar bill i

We terminated accounts associated with state-affiliated threat actors. Our findings show our models offer only limited, incremental capabilities for malicious c