{"id":"W4327939507","doi":"10.1016/j.fsidi.2023.301508","title":"On the prevalence of software supply chain attacks: Empirical study and investigative framework","year":2023,"lang":"en","type":"article","venue":"Forensic Science International Digital Investigation","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Malware; Computer science; False positive paradox; Software; Context (archaeology); Data mining; Computer security; Machine learning","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":[0.0102567,0.0003084727,0.0003861665,0.009817518,0.001143852,0.002619537,0.001559629,0.001656081,0.003836975],"category_scores_gemma":[0.1010401,0.0003644578,0.000496134,0.005544675,0.003042969,0.005390468,0.002421169,0.001640677,0.0004476923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036522,"about_ca_system_score_gemma":0.001007535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002493387,"about_ca_topic_score_gemma":0.002348354,"domain_scores_codex":[0.987377,0.006306018,0.001215856,0.001318356,0.002710973,0.001071812],"domain_scores_gemma":[0.6943858,0.2235051,0.06354995,0.006581489,0.01015578,0.001821847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006941516,0.000212056,0.9833215,0.00006523382,0.00006143711,0.0002154225,0.004025962,0.0003018497,0.0003484419,0.002784134,0.0002127264,0.008381668],"study_design_scores_gemma":[0.000007819446,0.0003395584,0.9596851,0.0002253979,0.0001463784,0.002674386,0.02584201,0.005776494,0.001274796,0.002461536,0.001529356,0.00003705332],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940038,0.0003138081,0.001029363,0.0002949782,0.000005008363,0.00003381856,0.0002250271,0.000006741237,0.004087409],"genre_scores_gemma":[0.9992468,0.0001345439,0.000307994,0.00002409556,0.00001112966,0.00001327171,0.00009958085,0.00000201944,0.0001606066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0102567,"threshold_uncertainty_score":0.05424321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04928924886908017,"score_gpt":0.3222360867124038,"score_spread":0.2729468378433237,"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."}}