{"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/membership-inference-attacks-against-2","title":"Membership Inference Attacks against Synthetic Data through Overfitting Detection","arxiv_id":"2302.12580","date":"2023-02-24","proceeding":null,"authors":["Boris van Breugel","Hao Sun","Zhaozhi Qian","Mihaela van der Schaar"],"abstract":"Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a potential solution. It aims to generate data that has the same distribution as the original data, but that does not disclose information about individuals. Membership Inference Attacks (MIAs) are a common privacy attack, in which the attacker attempts to determine whether a particular real sample was used for training of the model. Previous works that propose MIAs against generative models either display low performance -- giving the false impression that data is highly private -- or need to assume access to internal generative model parameters -- a relatively low-risk scenario, as the data publisher often only releases synthetic data, not the model. In this work we argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model. Experimentally we show that DOMIAS is significantly more successful at MIA than previous work, especially at attacking uncommon samples. The latter is disconcerting since these samples may correspond to underrepresented groups. We also demonstrate how DOMIAS' MIA performance score provides an interpretable metric for privacy, giving data publishers a new tool for achieving the desired privacy-utility trade-off in their synthetic data.","url_abs":"https://arxiv.org/abs/2302.12580v1","url_pdf":"https://arxiv.org/pdf/2302.12580v1.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":"membership-inference-attacks-against-2","repo_url":"https://github.com/vanderschaarlab/domias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.12580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12580"}},"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/vanderschaarlab/domias","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"883c31e7e7cb37f3","entry":"GAN_leaks","repo":"vanderschaarlab/domias","repo_kind":"official","path":"src/domias/baselines.py","file_url":"https://github.com/vanderschaarlab/domias/blob/HEAD/src/domias/baselines.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":"883c31e7e7cb37f3"}},{"code_sha256_prefix":"97176f9c559cc45f","entry":"compute_alpha_precision","repo":"vanderschaarlab/domias","repo_kind":"official","path":"src/domias/metrics/evaluation.py","file_url":"https://github.com/vanderschaarlab/domias/blob/HEAD/src/domias/metrics/evaluation.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":"97176f9c559cc45f"}},{"code_sha256_prefix":"8f9c330f5ce6bd85","entry":"d","repo":"vanderschaarlab/domias","repo_kind":"official","path":"src/domias/baselines.py","file_url":"https://github.com/vanderschaarlab/domias/blob/HEAD/src/domias/baselines.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":"8f9c330f5ce6bd85"}},{"code_sha256_prefix":"b2b257639c00245e","entry":"d_min","repo":"vanderschaarlab/domias","repo_kind":"official","path":"src/domias/baselines.py","file_url":"https://github.com/vanderschaarlab/domias/blob/HEAD/src/domias/baselines.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":"b2b257639c00245e"}},{"code_sha256_prefix":"7bf6fc70b69f9c4b","entry":"load_dataset","repo":"vanderschaarlab/domias","repo_kind":"official","path":"src/domias/bnaf/density_estimation.py","file_url":"https://github.com/vanderschaarlab/domias/blob/HEAD/src/domias/bnaf/density_estimation.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":"7bf6fc70b69f9c4b"}},{"code_sha256_prefix":"98ed3d40f8a5dfa5","entry":"save_model","repo":"vanderschaarlab/domias","repo_kind":"official","path":"src/domias/bnaf/density_estimation.py","file_url":"https://github.com/vanderschaarlab/domias/blob/HEAD/src/domias/bnaf/density_estimation.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":"98ed3d40f8a5dfa5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}