{"id":"W2767357856","doi":"10.1109/icsme.2017.77","title":"Evaluating State-of-the-Art Free and Open Source Static Analysis Tools Against Buffer Errors in Android Apps","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Android (operating system); Computer science; Static analysis; Malware; Mobile device; Computer security; Android malware; Malware analysis; Static program analysis; Buffer overflow; Operating system; Software","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009391,0.0001271543,0.0002921202,0.0001765047,0.0002639253,0.0005157537,0.002606549,0.00003222069,0.00001008575],"category_scores_gemma":[0.0007073872,0.00009832488,0.00006051979,0.0004256989,0.000103737,0.001432598,0.002627858,0.0001335043,0.000002484425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004496548,"about_ca_system_score_gemma":0.00004962957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002750856,"about_ca_topic_score_gemma":0.001230439,"domain_scores_codex":[0.9986402,0.0001186226,0.0003393028,0.0003995776,0.0002969209,0.0002053964],"domain_scores_gemma":[0.9976082,0.0001513392,0.0003416777,0.001749241,0.00009558904,0.00005398894],"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":[0.0000249593,0.00007724273,0.0188866,0.00003820377,0.0001428443,0.000007492784,0.001482205,0.01101891,0.004947802,0.001294515,0.0004515303,0.9616277],"study_design_scores_gemma":[0.001645292,0.0002884053,0.1131096,0.0001330203,0.00008835062,0.000007069988,0.0001815015,0.7496427,0.08966143,0.04327129,0.001303973,0.0006673231],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2751078,0.0000137883,0.7223415,0.0003737728,0.00003786823,0.0004082843,0.000003761294,0.00008043857,0.001632802],"genre_scores_gemma":[0.8051731,0.00001170417,0.1934276,0.0001954483,0.000003556479,0.00004546504,7.852585e-7,0.000008520658,0.001133754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9609604,"threshold_uncertainty_score":0.4973425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05763957363490184,"score_gpt":0.3602044797256012,"score_spread":0.3025649060906994,"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."}}