#AI safety
11 papers match
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Pingyu Wu, Lingyao Zhu, Weiming Zhang +1
The paper shows that safeguards for large language models that rely only on copyable context cannot guarantee reliable safety for dual‑use tasks, and proposes adding hard‑to‑copy t…
VETO: Towards Protecting Images From Frontier AI Editing
Jonas Grebe, Hossein Shakibania, Tobias Braun +2
The paper presents VETO, a subtle anti-edit cloak that disrupts how modern diffusion-based image editors read source images, and introduces VetoBench, a benchmark for evaluating pr…
Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks
Jeff Mohl, Nelson Gardner-Challis, Magda Dubois +6
The paper presents automated AI scanners that analyze benchmark transcripts to detect validity flaws such as ground‑truth leakage, tool failures, guessing vulnerabilities, and ambi…
A dataset of rated conceptual arguments
Emery Cooper, Caspar Oesterheld, Linh Chi Nguyen +2
The paper introduces a dataset of 951 expert‑rated argumentative critiques on 442 position texts covering AI safety, decision theory, ethics, and politics, and uses it to benchmark…
Why Public Service AI Governance Frameworks Risk Failing in the Age of General-Purpose AI: Lessons from Policing
Sam Relins, Daniel Birks
The paper argues that existing AI governance frameworks for public services, particularly policing, are inadequate for general‑purpose AI such as large language models because trad…
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
BuÄra Alperen Uluırmak, Rifat Kurban
The paper surveys recent work on evaluating large language models (LLMs) for safety and introduces the EvalSafetyGap framework to compare evaluation and alignment failures, illustr…