{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/revisiting-the-robust-alignment-of-circuit","title":"Revisiting the Robust Alignment of Circuit Breakers","arxiv_id":"2407.15902","date":"2024-07-22","proceeding":null,"authors":["Leo Schwinn","Simon Geisler"],"abstract":"Over the past decade, adversarial training has emerged as one of the few reliable methods for enhancing model robustness against adversarial attacks [Szegedy et al., 2014, Madry et al., 2018, Xhonneux et al., 2024], while many alternative approaches have failed to withstand rigorous subsequent evaluations. Recently, an alternative defense mechanism, namely \"circuit breakers\" [Zou et al., 2024], has shown promising results for aligning LLMs. In this report, we show that the robustness claims of \"Improving Alignment and Robustness with Circuit Breakers\" against unconstraint continuous attacks in the embedding space of the input tokens may be overestimated [Zou et al., 2024]. Specifically, we demonstrate that by implementing a few simple changes to embedding space attacks [Schwinn et al., 2024a,b], we achieve 100% attack success rate (ASR) against circuit breaker models. Without conducting any further hyperparameter tuning, these adjustments increase the ASR by more than 80% compared to the original evaluation. Code is accessible at: https://github.com/SchwinnL/circuit-breakers-eval","url_abs":"https://arxiv.org/abs/2407.15902v2","url_pdf":"https://arxiv.org/pdf/2407.15902v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"revisiting-the-robust-alignment-of-circuit","repo_url":"https://github.com/schwinnl/circuit-breakers-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.15902","atlas_url":"https://app.syntology.ai/?focus=2407.15902","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}