{"id":"W4323042475","doi":"10.1145/3585386","title":"VulANalyzeR: Explainable Binary Vulnerability Detection with Multi-task Learning and Attentional Graph Convolution","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Privacy and Security","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; McGill University; Queen's University","funders":"","keywords":"Computer science; Leverage (statistics); Vulnerability (computing); Machine learning; Artificial intelligence; Binary number; Binary classification; Deep learning; Task (project management); Software; Vulnerability assessment; Workload; Graph; Data mining; Theoretical computer science; Computer security; Support vector machine; Engineering","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":[0.0005285844,0.0001352775,0.0001278352,0.0002995484,0.0006270196,0.0001017482,0.0002363161,0.00007670791,0.000009952655],"category_scores_gemma":[0.0002083821,0.0001270865,0.00004108086,0.0008222326,0.00009608789,0.0004931571,0.00004498197,0.0004719562,0.00001063949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004680719,"about_ca_system_score_gemma":0.00002820197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007698471,"about_ca_topic_score_gemma":0.00003032279,"domain_scores_codex":[0.9987344,0.0001260523,0.0001385581,0.00046269,0.0002659021,0.0002724465],"domain_scores_gemma":[0.9988664,0.0005393415,0.00002981478,0.0003712894,0.00007830785,0.0001148276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001220221,0.002933115,0.4164118,0.002052285,0.001217469,0.0004178785,0.02333272,0.086247,0.03889078,0.003587163,0.0002340957,0.4234554],"study_design_scores_gemma":[0.002326946,0.0009548013,0.6024625,0.00008752043,0.00004385231,0.0001378254,0.0003490712,0.3796088,0.004090284,0.007816262,0.001489705,0.0006323805],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5295698,0.00005286085,0.469655,0.0002376222,0.00005557585,0.0001098549,0.000003026452,0.0003139141,0.000002293167],"genre_scores_gemma":[0.9954269,0.0001600338,0.004238475,0.00001129483,0.00001104698,0.00005838188,0.000006277109,0.000009604221,0.00007798467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4658571,"threshold_uncertainty_score":0.5182437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02061541211009944,"score_gpt":0.2717869745350305,"score_spread":0.2511715624249311,"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."}}