[2406.04313] Improving Alignment and Robustness with Circuit Breakers
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
[2406.04313] Improving Alignment and Robustness with Circuit Breakers 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:2406.04313 (cs) [Submitted on 6 Jun 2024 ( v1 ), last revised 12 Jul 2024 (this version, v4)] Title: Improving Alignment and Robustness with Circuit Breakers Authors: Andy Zou , Long Phan , Justin Wang , Derek Duenas , Maxwell Lin , Maksym Andriushchenko , Rowan Wang , Zico Kolter , Matt Fredrikson , Dan Hendrycks View a PDF of the paper title
Explore this link on the map →related reading
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Security incident disclosure — July 2026huggingface.co
- [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
- [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
- Refusal in LLMs is mediated by a single direction — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
- Mediumai-alignment.com
- Lapis Labslapis.rocks
- AI #77: A Few Upgrades - by Zvi Mowshowitzthezvi.substack.com
- AI Safety | Arkosevictoriabrook.github.io
- The Iliad Intensive Course Materials — LessWronglesswrong.com