{"id":"W4405562462","doi":"10.48550/arxiv.2412.12837","title":"Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Vulnerability (computing); Inference; Graph; Set (abstract data type); Key (lock); Artificial intelligence; Machine learning; Data science; Distributed computing; Theoretical computer science; Computer security","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007362574,0.0006314507,0.0009072211,0.001089752,0.001911444,0.003237365,0.001522871,0.00279792,0.001797598],"category_scores_gemma":[0.0385239,0.0006331746,0.0010111,0.0009134497,0.005264085,0.007204005,0.005267079,0.005010712,0.0003114785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002125414,"about_ca_system_score_gemma":0.0015327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001500858,"about_ca_topic_score_gemma":0.001120116,"domain_scores_codex":[0.9907669,0.005551521,0.0002669341,0.001272664,0.001672939,0.0004691663],"domain_scores_gemma":[0.9506154,0.03026903,0.004335394,0.01258116,0.001528193,0.0006709103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002393336,0.0001416809,0.005815628,0.0002032993,0.0001711128,0.0005686813,0.001261474,0.3604794,0.008364891,0.5664527,0.004662112,0.05163966],"study_design_scores_gemma":[0.00004122316,0.00006765992,0.0009587441,0.00003276548,0.00002436215,0.000248335,0.0001564997,0.5820871,0.00364275,0.4091239,0.003580059,0.00003663818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018251,0.0004227954,0.8827682,0.004915599,0.00007931259,0.0001370813,0.0001959385,0.0008128444,0.008843193],"genre_scores_gemma":[0.9337244,0.0002852717,0.0637922,0.0005104721,0.0001056368,0.0001248802,0.0001170492,0.0001002963,0.001239763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007362574,"threshold_uncertainty_score":0.03893751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1466755860421947,"score_gpt":0.2649599440972575,"score_spread":0.1182843580550628,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}