{"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/competition-report-finding-universal","title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs","arxiv_id":"2404.14461","date":"2024-04-22","proceeding":null,"authors":["Javier Rando","Francesco Croce","Kryštof Mitka","Stepan Shabalin","Maksym Andriushchenko","Nicolas Flammarion","Florian Tramèr"],"abstract":"Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.","url_abs":"https://arxiv.org/abs/2404.14461v2","url_pdf":"https://arxiv.org/pdf/2404.14461v2.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":"competition-report-finding-universal","repo_url":"https://github.com/ethz-spylab/rlhf_trojan_competition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"competition-report-finding-universal","repo_url":"https://github.com/neverix/rlhf-trojan-2024-cod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"misinformation","task_name":"Misinformation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.14461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14461"}},"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/neverix/rlhf-trojan-2024-cod","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ethz-spylab/rlhf_trojan_competition","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"60276a4baebeedd7","entry":"get_judgement_type","repo":"neverix/rlhf-trojan-2024-cod","repo_kind":"official","path":"method/generate_evaluate_completions.py","file_url":"https://github.com/neverix/rlhf-trojan-2024-cod/blob/HEAD/method/generate_evaluate_completions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60276a4baebeedd7"}},{"code_sha256_prefix":"42e3ef04a79bc40e","entry":"left_padding","repo":"ethz-spylab/rlhf_trojan_competition","repo_kind":"official","path":"src/datasets/base.py","file_url":"https://github.com/ethz-spylab/rlhf_trojan_competition/blob/HEAD/src/datasets/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42e3ef04a79bc40e"}},{"code_sha256_prefix":"23e03e9c588a5ae4","entry":"right_padding","repo":"ethz-spylab/rlhf_trojan_competition","repo_kind":"official","path":"src/datasets/base.py","file_url":"https://github.com/ethz-spylab/rlhf_trojan_competition/blob/HEAD/src/datasets/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23e03e9c588a5ae4"}},{"code_sha256_prefix":"da7adf6f4aa3c221","entry":"strip","repo":"neverix/rlhf-trojan-2024-cod","repo_kind":"official","path":"method/gadgets.py","file_url":"https://github.com/neverix/rlhf-trojan-2024-cod/blob/HEAD/method/gadgets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da7adf6f4aa3c221"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}