{"id":"W4413024210","doi":"10.1007/s11219-025-09727-2","title":"Investigating adversarial attacks in software analytics via machine learning explainability","year":2025,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Software analytics; Analytics; Computer science; Adversarial system; Software; Artificial intelligence; Software engineering; Machine learning; Data science; Software development; Software construction; Operating system","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":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006713177,0.0004384022,0.0007253532,0.0006158717,0.001059131,0.0005039972,0.001850265,0.0002925392,0.00006281168],"category_scores_gemma":[0.02038334,0.0004483873,0.0002966314,0.001793825,0.0002261608,0.00134307,0.001078855,0.003470383,0.00001655079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008084079,"about_ca_system_score_gemma":0.0007868223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004330295,"about_ca_topic_score_gemma":0.0001835879,"domain_scores_codex":[0.9935946,0.002284445,0.001519821,0.0008148109,0.0009117232,0.0008746293],"domain_scores_gemma":[0.9955427,0.002109006,0.0007909643,0.000822451,0.0004236218,0.000311256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003703893,0.000111269,0.7744151,0.0001351934,0.0000739831,0.00007694494,0.002272439,0.1418848,0.00004933737,0.003354205,0.0001436125,0.07744615],"study_design_scores_gemma":[0.008175482,0.0003891954,0.2938416,0.001127017,0.0001278261,0.0003229644,0.001487126,0.4606005,0.0003070106,0.2246816,0.006495264,0.002444381],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06186164,0.0002464135,0.9341301,0.001571724,0.001363699,0.0002039807,0.000003169364,0.0004579548,0.0001613632],"genre_scores_gemma":[0.612452,0.00001755599,0.3861357,0.0007350115,0.0003091601,0.00001014785,0.00001292712,0.00003166169,0.0002958376],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5505904,"threshold_uncertainty_score":0.9997968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02646495408055749,"score_gpt":0.3275634178778553,"score_spread":0.3010984637972978,"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."}}