{"id":"W4391620895","doi":"10.1109/tdsc.2024.3363507","title":"Data Poisoning Attacks and Defenses to LDP-Based Privacy-Preserving Crowdsensing","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Xiangtan University; National Natural Science Foundation of China","keywords":"Computer science; Differential privacy; Crowdsensing; Computer security; Minification; Identification (biology); Optimization problem; Data mining; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006782611,0.0003190249,0.00029927,0.0003615333,0.0009342982,0.001640151,0.0007047958,0.0001178478,0.000007305474],"category_scores_gemma":[0.00004230292,0.0003160551,0.00006366205,0.0006453452,0.00005265441,0.0006506576,0.0001005959,0.0005278495,0.00001528709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004507086,"about_ca_system_score_gemma":0.0001100713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001362107,"about_ca_topic_score_gemma":0.0001057238,"domain_scores_codex":[0.9975042,0.0001140182,0.0003606744,0.001158663,0.000311105,0.0005512761],"domain_scores_gemma":[0.9978126,0.0007186711,0.00005371362,0.001087161,0.00007082036,0.0002570932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004701212,0.0001175008,0.000139732,0.0007177463,0.0001915328,0.0005804507,0.006830469,0.2029941,0.01388645,0.00078935,0.00196369,0.771742],"study_design_scores_gemma":[0.0002276527,0.00008720641,0.00005555486,0.0009326335,0.00004029939,0.0002725774,0.0001653159,0.9854626,0.008243939,0.0001115401,0.004008248,0.0003923978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2067307,0.0007149249,0.7900256,0.0009870027,0.0006801812,0.0001701505,0.00001659976,0.0005212612,0.0001536024],"genre_scores_gemma":[0.9393502,0.00001820666,0.0599633,0.0004579754,0.00009170583,0.000002113697,0.000004019137,0.00003910915,0.00007329764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7824686,"threshold_uncertainty_score":0.9999291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03444357905367922,"score_gpt":0.2881141857485804,"score_spread":0.2536706066949012,"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."}}