Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution, and highlighting the need to move beyond risk recognition toward enforcing safety throughout execution.
Wei-Tao Feng, Heng-Heng Xiong, Zi-Hao Zeng et al.· 0 citations
Wide adoption of machine learning has created growing policy and regulatory demand for protecting sensitive training data, with differential privacy (DP) emerging as a key mechanism. Yet a less-studied problem is how to certify the faithful execution of DP during training: an external verifier should be able to check t...
SciGuard is proposed, an agent-based guardrail that employs large language models, tools and external knowledge to assess and control risks in scientific AI interactions, and achieves a state-of-the-art harmlessness score on red-teaming queries, while maintaining high performance on benign tasks, without sacrificing sc...
Jiyan He, Hao-Xiang Guan, Weitao Feng et al.· AI for Science· 26 citations· ⚡4
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.