{"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/harmbench-a-standardized-evaluation-framework","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","arxiv_id":"2402.04249","date":"2024-02-06","proceeding":null,"authors":["Mantas Mazeika","Long Phan","Xuwang Yin","Andy Zou","Zifan Wang","Norman Mu","Elham Sakhaee","Nathaniel Li","Steven Basart","Bo Li","David Forsyth","Dan Hendrycks"],"abstract":"Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods. To address this issue, we introduce HarmBench, a standardized evaluation framework for automated red teaming. We identify several desirable properties previously unaccounted for in red teaming evaluations and systematically design HarmBench to meet these criteria. Using HarmBench, we conduct a large-scale comparison of 18 red teaming methods and 33 target LLMs and defenses, yielding novel insights. We also introduce a highly efficient adversarial training method that greatly enhances LLM robustness across a wide range of attacks, demonstrating how HarmBench enables codevelopment of attacks and defenses. We open source HarmBench at https://github.com/centerforaisafety/HarmBench.","url_abs":"https://arxiv.org/abs/2402.04249v2","url_pdf":"https://arxiv.org/pdf/2402.04249v2.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":"abstracts"},"code_links":[{"paper_slug":"harmbench-a-standardized-evaluation-framework","repo_url":"https://github.com/centerforaisafety/harmbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"harmbench-a-standardized-evaluation-framework","repo_url":"https://github.com/guangyaodou/SSU_Unlearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"harmbench-a-standardized-evaluation-framework","repo_url":"https://github.com/matengsysu/himrd-jailbreak","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"red-teaming","task_name":"Red Teaming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.04249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04249"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/matengsysu/himrd-jailbreak","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guangyaodou/SSU_Unlearn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/centerforaisafety/harmbench","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"899b390c029421da","entry":"get_expanded_pipeline_configs","repo":"centerforaisafety/harmbench","repo_kind":"official","path":"scripts/run_pipeline.py","file_url":"https://github.com/centerforaisafety/harmbench/blob/HEAD/scripts/run_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"899b390c029421da"}},{"code_sha256_prefix":"11ac5d8b148a7915","entry":"run_subprocess_slurm","repo":"centerforaisafety/harmbench","repo_kind":"official","path":"scripts/run_pipeline.py","file_url":"https://github.com/centerforaisafety/harmbench/blob/HEAD/scripts/run_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11ac5d8b148a7915"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}