{"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/gradsafe-detecting-unsafe-prompts-for-llms","title":"GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis","arxiv_id":"2402.13494","date":"2024-02-21","proceeding":null,"authors":["Yueqi Xie","Minghong Fang","Renjie Pi","Neil Gong"],"abstract":"Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and resource-intensive data collection and training processes. In this study, we propose GradSafe, which effectively detects jailbreak prompts by scrutinizing the gradients of safety-critical parameters in LLMs. Our method is grounded in a pivotal observation: the gradients of an LLM's loss for jailbreak prompts paired with compliance response exhibit similar patterns on certain safety-critical parameters. In contrast, safe prompts lead to different gradient patterns. Building on this observation, GradSafe analyzes the gradients from prompts (paired with compliance responses) to accurately detect jailbreak prompts. We show that GradSafe, applied to Llama-2 without further training, outperforms Llama Guard, despite its extensive finetuning with a large dataset, in detecting jailbreak prompts. This superior performance is consistent across both zero-shot and adaptation scenarios, as evidenced by our evaluations on ToxicChat and XSTest. The source code is available at https://github.com/xyq7/GradSafe.","url_abs":"https://arxiv.org/abs/2402.13494v2","url_pdf":"https://arxiv.org/pdf/2402.13494v2.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":"gradsafe-detecting-unsafe-prompts-for-llms","repo_url":"https://github.com/xyq7/gradsafe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.13494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13494"}},"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/xyq7/gradsafe","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/xyq7/GradSafe","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"af8b68a12eeed276","entry":"find_critical_para","repo":"xyq7/GradSafe","repo_kind":"official","path":"code/find_critical_parameters.py","file_url":"https://github.com/xyq7/GradSafe/blob/HEAD/code/find_critical_parameters.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af8b68a12eeed276"}},{"code_sha256_prefix":"0763b555a75310d5","entry":"load_model","repo":"xyq7/GradSafe","repo_kind":"official","path":"code/find_critical_parameters.py","file_url":"https://github.com/xyq7/GradSafe/blob/HEAD/code/find_critical_parameters.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0763b555a75310d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}