AI Safety & Ethics

In the deepfake era, proving digital evidence is real requires experts public defenders cannot afford. Their indigent clients are the ones who will pay.

A pilot program to support independent safety and alignment research and develop the next generation of talent

Attorneys are in trouble for including AI-hallucinated legal citations in their court filings. How prevalent is this? I provide a numeric analysis. An AI Inside

arXiv:2604.02532v1 Announce Type: cross Abstract: Post-hoc feature attribution methods are widely deployed in safety-critical vision systems, yet their stabilit

arXiv:2604.02694v1 Announce Type: cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing ma

arXiv:2604.02912v1 Announce Type: cross Abstract: In January 2026, Anthropic published a 79-page "constitution" for its AI model Claude, the most comprehensive

arXiv:2604.03043v1 Announce Type: cross Abstract: In a healthcare environment, the healthcare interoperability platforms based on HL7 FHIR allow concurrent, asy

arXiv:2604.01449v2 Announce Type: replace Abstract: Artificial intelligence (AI) systems are increasingly integrated into healthcare and pharmacy workflows, sup

arXiv:2512.13907v3 Announce Type: replace-cross Abstract: The implementation of the AI Act requires practical mechanisms to verify compliance with legal obligat

Governor Kathy Hochul and other New York state lawmakers want 3D-printer companies to block the printing of components used to create "ghost guns" - firearms wi

Gatling-type weapons like the U.S. C-RAM can be presented as an invincible shield against drones. But some Shaheds are getting through due to the weapon's limit

AI already favors self-preservation. New research shows that AI favors peer-preservations too. This is troubling. AI safety issues arise, An AI Insider scoop.

arXiv:2604.00072v1 Announce Type: cross Abstract: Can classifier-based safety gates maintain reliable oversight as AI systems improve over hundreds of iteration

arXiv:2604.00324v1 Announce Type: cross Abstract: Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This t

arXiv:2604.01052v1 Announce Type: cross Abstract: "Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little

arXiv:2411.10174v2 Announce Type: replace-cross Abstract: During the past decade, Deep Neural Networks (DNNs) proved their value on a large variety of subjects.

arXiv:2603.20897v2 Announce Type: replace-cross Abstract: The strong and continuous increase of AI-based services leads to the steady proliferation of AI data c

When a tech company draws a moral line, follow the money first — and ask questions later. Because the uncomfortable truth is that every major AI company today s

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