{"id":"W4403582747","doi":"10.1145/3627673.3679726","title":"Dynamic Neural Control Flow Execution: an Agent-Based Deep Equilibrium Approach for Binary Vulnerability Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; Blackberry (Canada); McGill University; Queen's University","funders":"","keywords":"Computer science; Vulnerability (computing); Binary number; Flow (mathematics); Control (management); Control flow; Artificial neural network; Artificial intelligence; Computer security; Mathematics","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":[0.0008470978,0.0002349892,0.0002170174,0.0001635484,0.0002452439,0.0003960401,0.0006637591,0.0001243855,0.00002718305],"category_scores_gemma":[0.0001213093,0.0002106137,0.0001771923,0.000481787,0.00007159953,0.00116337,0.000121774,0.0003453382,0.000009820974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001960681,"about_ca_system_score_gemma":0.00008557353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000287327,"about_ca_topic_score_gemma":0.0000154215,"domain_scores_codex":[0.9978217,0.0003177601,0.0002973348,0.0008723209,0.0002838332,0.0004070865],"domain_scores_gemma":[0.9987755,0.0002920285,0.00005354863,0.0006617706,0.00008732921,0.0001298604],"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":[0.00006585631,0.00007533259,0.00006282591,0.00009640722,0.00001791217,0.000008627395,0.0001035032,0.9180218,0.004030295,0.001177699,0.00001911378,0.07632061],"study_design_scores_gemma":[0.0006786286,0.0003105475,0.0002835304,0.000006299241,0.00002455001,0.00001496562,0.00002934629,0.9973484,0.0003064672,0.0006089797,0.0001361631,0.0002521787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01549232,0.0001039452,0.9801202,0.0006550465,0.001462496,0.0006398634,0.000006081086,0.001290567,0.0002295188],"genre_scores_gemma":[0.7739165,1.7128e-7,0.2255118,0.000173212,0.0001311071,0.000118039,0.00003518407,0.00002212483,0.00009184552],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7584242,"threshold_uncertainty_score":0.8588575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01563875621875029,"score_gpt":0.2803951293155705,"score_spread":0.2647563730968202,"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."}}