[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

related reading

• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2406.17583] Towards Compositional Interpretability for XAIarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2407.15549] Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMsarxiv.org
• [2404.01413v2] Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Dataarxiv.org
• [2402.04249] HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalarxiv.org
• [2309.00236] Image Hijacks: Adversarial Images can Control Generative Models at Runtimearxiv.org
• [2506.00751] Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?arxiv.org
• Hyper-Connectionsarxiv.org
• [2508.12773] Online Ensemble Transformer for Accurate Cloud Workload Forecasting in Predictive Auto-Scalingarxiv.org