{"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/leave-one-out-distinguishability-in-machine","title":"Leave-one-out Distinguishability in Machine Learning","arxiv_id":"2309.17310","date":"2023-09-29","proceeding":null,"authors":["Jiayuan Ye","Anastasia Borovykh","Soufiane Hayou","Reza Shokri"],"abstract":"We introduce an analytical framework to quantify the changes in a machine learning algorithm's output distribution following the inclusion of a few data points in its training set, a notion we define as leave-one-out distinguishability (LOOD). This is key to measuring data **memorization** and information **leakage** as well as the **influence** of training data points in machine learning. We illustrate how our method broadens and refines existing empirical measures of memorization and privacy risks associated with training data. We use Gaussian processes to model the randomness of machine learning algorithms, and validate LOOD with extensive empirical analysis of leakage using membership inference attacks. Our analytical framework enables us to investigate the causes of leakage and where the leakage is high. For example, we analyze the influence of activation functions, on data memorization. Additionally, our method allows us to identify queries that disclose the most information about the training data in the leave-one-out setting. We illustrate how optimal queries can be used for accurate **reconstruction** of training data.","url_abs":"https://arxiv.org/abs/2309.17310v4","url_pdf":"https://arxiv.org/pdf/2309.17310v4.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":"leave-one-out-distinguishability-in-machine","repo_url":"https://github.com/privacytrustlab/lood_in_ml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"leave-one-out-distinguishability-in-machine","repo_url":"https://github.com/marcuslassila/mia-audit-gnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"memorization","task_name":"Memorization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.17310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17310"}},"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/privacytrustlab/lood_in_ml","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marcuslassila/mia-audit-gnn","reach":null}],"summary":{"ran":2,"ran_violates":3,"ran_honours":2,"ran_fixture":1,"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":13,"ran":8,"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":"8682d43ff7f3052a","entry":"TrainConfig","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.py","link_basis":"first_harvest_node","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":"8682d43ff7f3052a"}},{"code_sha256_prefix":"ddc730f825d30aeb","entry":"cross_entropy","repo":"privacytrustlab/lood_in_ml","repo_kind":"official","path":"exact_nngp/compute_LOOD.py","file_url":"https://github.com/privacytrustlab/lood_in_ml/blob/HEAD/exact_nngp/compute_LOOD.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ddc730f825d30aeb"}},{"code_sha256_prefix":"af3b24c0d1df242e","entry":"gaussian_kl_divergence","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af3b24c0d1df242e"}},{"code_sha256_prefix":"860cf41704a441fd","entry":"k_hop_query","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"860cf41704a441fd"}},{"code_sha256_prefix":"9a6e2d5cad2883cd","entry":"masked_subgraph","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"9a6e2d5cad2883cd"}},{"code_sha256_prefix":"be09318c6244ea19","entry":"mse_loss_acc_fn","repo":"privacytrustlab/lood_in_ml","repo_kind":"official","path":"exact_nngp/compute_LOOD.py","file_url":"https://github.com/privacytrustlab/lood_in_ml/blob/HEAD/exact_nngp/compute_LOOD.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be09318c6244ea19"}},{"code_sha256_prefix":"6bbaf642c5710a82","entry":"multi_gaussian_kl_divergence","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bbaf642c5710a82"}},{"code_sha256_prefix":"6986149c1865e125","entry":"to_cuda","repo":"privacytrustlab/lood_in_ml","repo_kind":"official","path":"FC_MIA/compute_auc_and_diff.py","file_url":"https://github.com/privacytrustlab/lood_in_ml/blob/HEAD/FC_MIA/compute_auc_and_diff.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6986149c1865e125"}},{"code_sha256_prefix":"312d10ceb8442d70","entry":"train_gnn","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"312d10ceb8442d70"}},{"code_sha256_prefix":"6e86451052b11f1a","entry":"train_split_interconnection_mask","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e86451052b11f1a"}},{"code_sha256_prefix":"e7b5e1f562be899b","entry":"valid_step_gnn","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.py","link_basis":"first_harvest_node","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":"e7b5e1f562be899b"}},{"code_sha256_prefix":"ced15d198fbc913f","entry":"LOOD","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"ced15d198fbc913f"}},{"code_sha256_prefix":"01fc4c2299894c2d","entry":"fresh_model","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"01fc4c2299894c2d"}},{"code_sha256_prefix":"46491b355211dca6","entry":"plot_histogram_and_fitted_gaussian","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"46491b355211dca6"}},{"code_sha256_prefix":"d87f450c3b155b93","entry":"savefig_or_show","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"d87f450c3b155b93"}},{"code_sha256_prefix":"27ead46c9420e337","entry":"train_step_gnn","repo":"marcuslassila/mia-audit-gnn","repo_kind":"listed","path":"src/lood.py","file_url":"https://github.com/marcuslassila/mia-audit-gnn/blob/HEAD/src/lood.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":"27ead46c9420e337"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}