{"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/variational-model-inversion-attacks-1","title":"Variational Model Inversion Attacks","arxiv_id":"2201.10787","date":"2022-01-26","proceeding":"NeurIPS 2021 12","authors":["Kuan-Chieh Wang","Yan Fu","Ke Li","Ashish Khisti","Richard Zemel","Alireza Makhzani"],"abstract":"Given the ubiquity of deep neural networks, it is important that these models do not reveal information about sensitive data that they have been trained on. In model inversion attacks, a malicious user attempts to recover the private dataset used to train a supervised neural network. A successful model inversion attack should generate realistic and diverse samples that accurately describe each of the classes in the private dataset. In this work, we provide a probabilistic interpretation of model inversion attacks, and formulate a variational objective that accounts for both diversity and accuracy. In order to optimize this variational objective, we choose a variational family defined in the code space of a deep generative model, trained on a public auxiliary dataset that shares some structural similarity with the target dataset. Empirically, our method substantially improves performance in terms of target attack accuracy, sample realism, and diversity on datasets of faces and chest X-ray images.","url_abs":"https://arxiv.org/abs/2201.10787v1","url_pdf":"https://arxiv.org/pdf/2201.10787v1.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":"variational-model-inversion-attacks-1","repo_url":"https://github.com/wangkua1/vmi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.10787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10787"}},"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/wangkua1/vmi","reach":null}],"summary":{"ran_fixture":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":3,"samples":[{"code_sha256_prefix":"938f526f1995a88d","entry":"add_color_border","repo":"wangkua1/vmi","repo_kind":"official","path":"evaluate_samples.py","file_url":"https://github.com/wangkua1/vmi/blob/HEAD/evaluate_samples.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"938f526f1995a88d"}},{"code_sha256_prefix":"44f8073d78252a7a","entry":"compute_entropy","repo":"wangkua1/vmi","repo_kind":"official","path":"evaluate_samples.py","file_url":"https://github.com/wangkua1/vmi/blob/HEAD/evaluate_samples.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44f8073d78252a7a"}},{"code_sha256_prefix":"5cc15dbbae703454","entry":"compute_kl","repo":"wangkua1/vmi","repo_kind":"official","path":"evaluate_samples.py","file_url":"https://github.com/wangkua1/vmi/blob/HEAD/evaluate_samples.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5cc15dbbae703454"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}