{"id":"W4416799874","doi":"10.1109/snpd65828.2025.11252836","title":"Deep Learning-based Binary Analysis for Vulnerability Detection in x86-64 Machine Code","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Vulnerability (computing); Code (set theory); Task (project management); Deep learning; Vulnerability assessment; Source code; Control flow; Control (management)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00190345,0.0005059064,0.0008283659,0.002661685,0.0006095127,0.000225337,0.0009159401,0.0003766272,0.0001497562],"category_scores_gemma":[0.001005725,0.0005487389,0.0006305871,0.009051733,0.000181161,0.0006595999,0.0003683275,0.0009077113,0.000007387846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008261089,"about_ca_system_score_gemma":0.0001937489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006042872,"about_ca_topic_score_gemma":0.009252357,"domain_scores_codex":[0.995391,0.0006709546,0.0011525,0.001707988,0.0003644089,0.0007131867],"domain_scores_gemma":[0.996747,0.001000826,0.00036941,0.001296509,0.0004462571,0.0001400484],"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":[0.0003853137,0.0004703438,0.0112379,0.0001888959,0.0002224983,0.000006826572,0.0001019012,0.5719453,0.002791304,0.0006365993,0.00001333502,0.4119998],"study_design_scores_gemma":[0.0008882649,0.0007002087,0.009081248,0.00003365405,0.0002034189,0.000001033085,0.00003094309,0.8616433,0.1209379,0.004088539,0.001964269,0.0004272374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008086026,0.0003794405,0.9873055,0.0008016622,0.000514275,0.001370958,0.000009911148,0.00114638,0.0003859035],"genre_scores_gemma":[0.9107731,0.00003791553,0.08694393,0.0004241286,0.00002724394,0.0005012051,0.00001359341,0.00002256647,0.001256328],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9026871,"threshold_uncertainty_score":0.9996964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01281872135784416,"score_gpt":0.3011599710382058,"score_spread":0.2883412496803616,"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."}}