✳flâneur — a map of the web's best reading

[2407.21792] Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

arxiv.org · 754 words · saved by 1 readers

Influence flowers are visualizations for citation influences among academic entities, including papers, authors, institutions, and research topics. See here for more detail. Loading... arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2407.21792] Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2407.21792 (cs) [Submitted on 31 Jul 2024 ( v1 ), last revised 27 Dec 2024 (this version, v3)] Title: Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? Authors: Richard Ren , Steven Basart , Adam Khoja , Alice Gatti , Long Phan , Xuwang Yin , Mantas Mazeika , Alexander Pan , Gabriel Mukobi , Ryan H. Kim ,

Explore this link on the map →

related reading