{"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/bypassing-the-safety-training-of-open-source","title":"Bypassing the Safety Training of Open-Source LLMs with Priming Attacks","arxiv_id":"2312.12321","date":"2023-12-19","proceeding":null,"authors":["Jason Vega","Isha Chaudhary","Changming Xu","Gagandeep Singh"],"abstract":"With the recent surge in popularity of LLMs has come an ever-increasing need for LLM safety training. In this paper, we investigate the fragility of SOTA open-source LLMs under simple, optimization-free attacks we refer to as $\\textit{priming attacks}$, which are easy to execute and effectively bypass alignment from safety training. Our proposed attack improves the Attack Success Rate on Harmful Behaviors, as measured by Llama Guard, by up to $3.3\\times$ compared to baselines. Source code and data are available at https://github.com/uiuc-focal-lab/llm-priming-attacks.","url_abs":"https://arxiv.org/abs/2312.12321v2","url_pdf":"https://arxiv.org/pdf/2312.12321v2.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":"bypassing-the-safety-training-of-open-source","repo_url":"https://github.com/uiuc-focal-lab/llm-priming-attacks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.12321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12321"}},"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/uiuc-focal-lab/llm-priming-attacks","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"593fd66f8b7ced2c","entry":"get_prompt_message","repo":"uiuc-focal-lab/llm-priming-attacks","repo_kind":"official","path":"attack_llama.py","file_url":"https://github.com/uiuc-focal-lab/llm-priming-attacks/blob/HEAD/attack_llama.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":"593fd66f8b7ced2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}