{"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/multi-step-jailbreaking-privacy-attacks-on","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","arxiv_id":"2304.05197","date":"2023-04-11","proceeding":null,"authors":["Haoran Li","Dadi Guo","Wei Fan","Mingshi Xu","Jie Huang","Fanpu Meng","Yangqiu Song"],"abstract":"With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from LLMs, it is still challenging to steer AI-generated content (AIGC) for the human good. As powerful LLMs are devouring existing text data from various domains (e.g., GPT-3 is trained on 45TB texts), it is natural to doubt whether the private information is included in the training data and what privacy threats can these LLMs and their downstream applications bring. In this paper, we study the privacy threats from OpenAI's ChatGPT and the New Bing enhanced by ChatGPT and show that application-integrated LLMs may cause new privacy threats. To this end, we conduct extensive experiments to support our claims and discuss LLMs' privacy implications.","url_abs":"https://arxiv.org/abs/2304.05197v3","url_pdf":"https://arxiv.org/pdf/2304.05197v3.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":"multi-step-jailbreaking-privacy-attacks-on","repo_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"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=2304.05197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05197"}},"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/hkust-knowcomp/llm-multistep-jailbreak","reach":null}],"summary":{"ran_draft_wrong":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"32b07d89411c2e88","entry":"get_input_msg","repo":"hkust-knowcomp/llm-multistep-jailbreak","repo_kind":"official","path":"chatgpt_extraction.py","file_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak/blob/HEAD/chatgpt_extraction.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":"32b07d89411c2e88"}},{"code_sha256_prefix":"04a8740098e56b35","entry":"get_input_msg","repo":"hkust-knowcomp/llm-multistep-jailbreak","repo_kind":"official","path":"llm_extraction.py","file_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak/blob/HEAD/llm_extraction.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":"04a8740098e56b35"}},{"code_sha256_prefix":"bcd8ea8ff949ee79","entry":"get_mc_prompt","repo":"hkust-knowcomp/llm-multistep-jailbreak","repo_kind":"official","path":"chatgpt_extraction.py","file_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak/blob/HEAD/chatgpt_extraction.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":"bcd8ea8ff949ee79"}},{"code_sha256_prefix":"1d5a26fef3259c5c","entry":"get_prompt_from_type","repo":"hkust-knowcomp/llm-multistep-jailbreak","repo_kind":"official","path":"chatgpt_extraction.py","file_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak/blob/HEAD/chatgpt_extraction.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":"1d5a26fef3259c5c"}},{"code_sha256_prefix":"9f63cd22698d1af1","entry":"get_prompt_from_type","repo":"hkust-knowcomp/llm-multistep-jailbreak","repo_kind":"official","path":"llm_extraction.py","file_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak/blob/HEAD/llm_extraction.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":"9f63cd22698d1af1"}},{"code_sha256_prefix":"1d3b9f0c41c6e364","entry":"get_mc_prompt","repo":"hkust-knowcomp/llm-multistep-jailbreak","repo_kind":"official","path":"llm_extraction.py","file_url":"https://github.com/hkust-knowcomp/llm-multistep-jailbreak/blob/HEAD/llm_extraction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d3b9f0c41c6e364"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}