{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006397241,0.00168606,0.0008433942,0.0009760314,0.0003380759,0.0007791051,0.002242675,0.001671694,0.002240313],"category_scores_gemma":[0.002329129,0.0006179452,0.00115317,0.0006435476,0.0005643199,0.001646508,0.001415986,0.001959858,0.000704738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001178574,"about_ca_system_score_gemma":0.001209438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01259501,"about_ca_topic_score_gemma":0.01662695,"domain_scores_codex":[0.9997037,0.00004811079,0.00001092296,0.0001274858,0.00005100175,0.00005864021],"domain_scores_gemma":[0.9993259,0.0003515103,0.00007650391,0.0001146968,0.00008131374,0.00005009308],"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":[0.0004194421,0.0004253715,0.005477302,0.0002312133,0.0002776978,0.000347622,0.0001330743,0.5445051,0.0118434,0.00493089,0.01810361,0.4133053],"study_design_scores_gemma":[0.00001002985,0.00002545039,0.0002077764,0.000003831314,0.000009952523,0.00001806736,0.000004668695,0.9958398,0.0009989311,0.002566468,0.000309735,0.000005155133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.136201,0.001667961,0.8284348,0.001116288,0.0001810047,0.0001894482,0.001366283,0.02802537,0.002817813],"genre_scores_gemma":[0.7856835,0.000496489,0.2024859,0.0008551083,0.00009986162,0.0002261336,0.003457724,0.0005608611,0.006134511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01259501,"threshold_uncertainty_score":0.02504337,"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."}}