{"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/secretgen-privacy-recovery-on-pre-trained","title":"SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination","arxiv_id":"2207.12263","date":"2022-07-25","proceeding":null,"authors":["Zhuowen Yuan","Fan Wu","Yunhui Long","Chaowei Xiao","Bo Li"],"abstract":"Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises extensive concerns on whether these pre-trained models would leak privacy-sensitive information of their training data. Thus, in this work, we aim to answer the following questions: \"Can we effectively recover private information from these pre-trained models? What are the sufficient conditions to retrieve such sensitive information?\" We first explore different statistical information which can discriminate the private training distribution from other distributions. Based on our observations, we propose a novel private data reconstruction framework, SecretGen, to effectively recover private information. Compared with previous methods which can recover private data with the ground true prediction of the targeted recovery instance, SecretGen does not require such prior knowledge, making it more practical. We conduct extensive experiments on different datasets under diverse scenarios to compare SecretGen with other baselines and provide a systematic benchmark to better understand the impact of different auxiliary information and optimization operations. We show that without prior knowledge about true class prediction, SecretGen is able to recover private data with similar performance compared with the ones that leverage such prior knowledge. If the prior knowledge is given, SecretGen will significantly outperform baseline methods. We also propose several quantitative metrics to further quantify the privacy vulnerability of pre-trained models, which will help the model selection for privacy-sensitive applications. Our code is available at: https://github.com/AI-secure/SecretGen.","url_abs":"https://arxiv.org/abs/2207.12263v1","url_pdf":"https://arxiv.org/pdf/2207.12263v1.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":"secretgen-privacy-recovery-on-pre-trained","repo_url":"https://github.com/ai-secure/secretgen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2207.12263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12263"}},"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":"deterministic:regex_extraction","url":"https://github.com/AI-secure/SecretGen","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"ran":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"7d8eaf5537f699e4","entry":"np2th","repo":"AI-secure/SecretGen","repo_kind":"official","path":"tgt_models/vit.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/tgt_models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d8eaf5537f699e4"}},{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"AI-secure/SecretGen","repo_kind":"official","path":"tgt_models/vit.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/tgt_models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"5ef80f92b298862d","entry":"dconv_bn_relu","repo":"AI-secure/SecretGen","repo_kind":"official","path":"models.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ef80f92b298862d"}},{"code_sha256_prefix":"ad5dbf57f3ea2633","entry":"get_block","repo":"AI-secure/SecretGen","repo_kind":"official","path":"facenet.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/facenet.py","link_basis":"harvester_set","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":"ad5dbf57f3ea2633"}},{"code_sha256_prefix":"ea7941eb1ea8ffb2","entry":"get_blocks","repo":"AI-secure/SecretGen","repo_kind":"official","path":"facenet.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/facenet.py","link_basis":"harvester_set","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":"ea7941eb1ea8ffb2"}},{"code_sha256_prefix":"c54fea429589425d","entry":"l2_norm","repo":"AI-secure/SecretGen","repo_kind":"official","path":"facenet.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/facenet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c54fea429589425d"}},{"code_sha256_prefix":"32a2722356ae35ea","entry":"noise_loss","repo":"AI-secure/SecretGen","repo_kind":"official","path":"losses.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32a2722356ae35ea"}},{"code_sha256_prefix":"8ceea87fe22a6f64","entry":"completion_network_loss","repo":"AI-secure/SecretGen","repo_kind":"official","path":"losses.py","file_url":"https://github.com/AI-secure/SecretGen/blob/HEAD/losses.py","link_basis":"harvester_set","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":"8ceea87fe22a6f64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}