{"id":"W3048511744","doi":"10.1145/3383313.3412243","title":"Revisiting Adversarially Learned Injection Attacks Against Recommender Systems","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transferability; Recommender system; Relevance (law); Computer security; Attack model; Machine learning","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001363831,0.0006371622,0.0008550517,0.0002731698,0.000369849,0.001201781,0.002582873,0.0006386102,0.000038358],"category_scores_gemma":[0.0008884489,0.0006598168,0.0003176061,0.0005391455,0.00004261659,0.0006190878,0.006112882,0.002864815,0.0001967179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004500278,"about_ca_system_score_gemma":0.0004241043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004364815,"about_ca_topic_score_gemma":0.000005176085,"domain_scores_codex":[0.9949913,0.0009001949,0.0009587746,0.001796527,0.0007535247,0.0005996716],"domain_scores_gemma":[0.9967057,0.0003465523,0.0009176558,0.001515067,0.0002607657,0.0002542592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002439648,0.00002315579,0.0005913868,0.0005231457,0.0002064262,0.00006063566,0.001062067,0.9076026,0.00008230552,0.02885144,0.003967061,0.05700539],"study_design_scores_gemma":[0.0004770926,0.00005105404,0.0001770095,0.0004632467,0.0000392584,0.00001595519,0.0002458367,0.9839342,0.00002286698,0.001634713,0.01208531,0.0008534137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004559889,0.0001754016,0.9377828,0.007313373,0.007038019,0.0006608758,0.000003854711,0.00179884,0.04477086],"genre_scores_gemma":[0.8107886,0.0001736441,0.1787604,0.002590137,0.005441376,0.0001096295,0.0001629881,0.0001706977,0.001802601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8103325,"threshold_uncertainty_score":0.9998351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05730140208896777,"score_gpt":0.3096711468692656,"score_spread":0.2523697447802978,"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."}}