{"id":"W4406488692","doi":"10.7717/peerj-cs.2504","title":"MSSA: multi-stage semantic-aware neural network for binary code similarity detection","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre Scientifique et Technique du Bâtiment; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Binary code; Binary number; Artificial neural network; Artificial intelligence; Transformer; Semantics (computer science); Code (set theory); Source code; Semantic similarity; Deep learning; Machine learning; Data mining; Pattern recognition (psychology); Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000388151,0.001518334,0.0007355319,0.001150963,0.0004354473,0.000564661,0.001560959,0.0008923617,0.002231474],"category_scores_gemma":[0.001241686,0.0003694934,0.0007598128,0.0007329356,0.0004075941,0.001568588,0.0009976684,0.001253976,0.001173943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000873878,"about_ca_system_score_gemma":0.001062958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009890039,"about_ca_topic_score_gemma":0.01680304,"domain_scores_codex":[0.9997316,0.00003351128,0.00001627799,0.00008708594,0.00007917922,0.00005235858],"domain_scores_gemma":[0.9996928,0.00007207524,0.0000362379,0.00003951371,0.000131743,0.00002775622],"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":[0.0006021481,0.0005052795,0.006365872,0.0002103088,0.0002098254,0.0002103886,0.0001130123,0.1637967,0.02594431,0.003896671,0.02087724,0.7772682],"study_design_scores_gemma":[0.00001132366,0.00007033825,0.0006980725,0.000007620331,0.00002633105,0.00004483858,0.00001927479,0.9913309,0.004655422,0.002177422,0.0009476729,0.00001081399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2219336,0.002481344,0.7431759,0.0009327484,0.0005311471,0.0002765234,0.0023899,0.02018621,0.008092694],"genre_scores_gemma":[0.8255256,0.0005538321,0.156876,0.0005541885,0.0001335885,0.0002315347,0.004962671,0.0002606581,0.01090194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009890039,"threshold_uncertainty_score":0.01966494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03622750143753793,"score_gpt":0.3262810718075838,"score_spread":0.2900535703700459,"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."}}