{"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/intention-analysis-prompting-makes-large","title":"Intention Analysis Makes LLMs A Good Jailbreak Defender","arxiv_id":"2401.06561","date":"2024-01-12","proceeding":null,"authors":["Yuqi Zhang","Liang Ding","Lefei Zhang","DaCheng Tao"],"abstract":"Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks, which limits their effectiveness in such complex scenarios. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis ($\\mathbb{IA}$). $\\mathbb{IA}$ works by triggering LLMs' inherent self-correct and improve ability through a two-stage process: 1) analyzing the essential intention of the user input, and 2) providing final policy-aligned responses based on the first round conversation. Notably, $\\mathbb{IA}$ is an inference-only method, thus could enhance LLM safety without compromising their helpfulness. Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that $\\mathbb{IA}$ could consistently and significantly reduce the harmfulness in responses (averagely -48.2% attack success rate). Encouragingly, with our $\\mathbb{IA}$, Vicuna-7B even outperforms GPT-3.5 regarding attack success rate. We empirically demonstrate that, to some extent, $\\mathbb{IA}$ is robust to errors in generated intentions. Further analyses reveal the underlying principle of $\\mathbb{IA}$: suppressing LLM's tendency to follow jailbreak prompts, thereby enhancing safety.","url_abs":"https://arxiv.org/abs/2401.06561v4","url_pdf":"https://arxiv.org/pdf/2401.06561v4.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":"intention-analysis-prompting-makes-large","repo_url":"https://github.com/alphadl/safellm_with_intentionanalysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.06561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06561"}},"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/alphadl/safellm_with_intentionanalysis","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"9ec48e73fc2bd33f","entry":"get_conv_template","repo":"alphadl/safellm_with_intentionanalysis","repo_kind":"official","path":"demo/conversation.py","file_url":"https://github.com/alphadl/safellm_with_intentionanalysis/blob/HEAD/demo/conversation.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":"9ec48e73fc2bd33f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}