{"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/making-them-a-malicious-database-exploiting","title":"QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language","arxiv_id":"2502.09723","date":"2025-02-13","proceeding":null,"authors":["Qingsong Zou","Jingyu Xiao","Qing Li","Zhi Yan","Yuhang Wang","Li Xu","Wenxuan Wang","Kuofeng Gao","Ruoyu Li","Yong Jiang"],"abstract":"Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety alignment are developed for defense, prior researches reveal the possibility of bypassing such defenses through well-designed jailbreak attacks. In this paper, we propose QueryAttack, a novel framework to examine the generalizability of safety alignment. By treating LLMs as knowledge databases, we translate malicious queries in natural language into structured non-natural query language to bypass the safety alignment mechanisms of LLMs. We conduct extensive experiments on mainstream LLMs, and the results show that QueryAttack not only can achieve high attack success rates (ASRs), but also can jailbreak various defense methods. Furthermore, we tailor a defense method against QueryAttack, which can reduce ASR by up to $64\\%$ on GPT-4-1106. Our code is available at https://github.com/horizonsinzqs/QueryAttack.","url_abs":"https://arxiv.org/abs/2502.09723v3","url_pdf":"https://arxiv.org/pdf/2502.09723v3.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":"making-them-a-malicious-database-exploiting","repo_url":"https://github.com/horizonsinzqs/queryattack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"safety-alignment","task_name":"Safety Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.09723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09723"}},"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/horizonsinzqs/queryattack","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"36d4f4fdeeda8117","entry":"extract_content","repo":"horizonsinzqs/queryattack","repo_kind":"official","path":"evaluate_responses.py","file_url":"https://github.com/horizonsinzqs/queryattack/blob/HEAD/evaluate_responses.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36d4f4fdeeda8117"}},{"code_sha256_prefix":"2c0ee7a2a2e894e8","entry":"load_data","repo":"horizonsinzqs/queryattack","repo_kind":"official","path":"translator.py","file_url":"https://github.com/horizonsinzqs/queryattack/blob/HEAD/translator.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":"2c0ee7a2a2e894e8"}},{"code_sha256_prefix":"3ff749b86c2c8aa8","entry":"load_problems","repo":"horizonsinzqs/queryattack","repo_kind":"official","path":"evaluate_responses.py","file_url":"https://github.com/horizonsinzqs/queryattack/blob/HEAD/evaluate_responses.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":"3ff749b86c2c8aa8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}