{"id":"W7110431310","doi":"10.1145/3721462.3770770","title":"Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing","year":2025,"lang":"en","type":"article","venue":"","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":"Vulnerability (computing); Inference; Through-the-lens metering; Graph; Set (abstract data type); Mixing (physics); Differential privacy; Node (physics)","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":[0.007770842,0.0007445286,0.001049893,0.001108148,0.002087583,0.003474334,0.001754508,0.002981051,0.001629762],"category_scores_gemma":[0.04098694,0.0007616124,0.001201526,0.0009603611,0.00556511,0.0077414,0.005904362,0.005800615,0.0002766354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002104715,"about_ca_system_score_gemma":0.001672345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001395711,"about_ca_topic_score_gemma":0.0009759937,"domain_scores_codex":[0.9895997,0.005846555,0.000332084,0.001546853,0.002113852,0.0005609479],"domain_scores_gemma":[0.9494423,0.02864191,0.004475281,0.01522297,0.001543754,0.0006738414],"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":[0.0002167091,0.0001239854,0.004823513,0.0001939815,0.0001735861,0.0005775354,0.001301456,0.3413703,0.009102902,0.5987031,0.002983234,0.04042967],"study_design_scores_gemma":[0.00003743791,0.00007079016,0.0007565118,0.00003468167,0.00002686105,0.0002815426,0.0001559321,0.6072631,0.004504985,0.3836937,0.003136856,0.00003760451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06943528,0.0002834963,0.9203066,0.002982524,0.0000551541,0.0001405594,0.0001350211,0.0005825066,0.006078755],"genre_scores_gemma":[0.9194987,0.0002541394,0.07825896,0.0004084838,0.00009021972,0.000146815,0.00009887931,0.000089032,0.001154753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007770842,"threshold_uncertainty_score":0.04109663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06281523797579446,"score_gpt":0.3410532106459956,"score_spread":0.2782379726702012,"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."}}