{"id":"W3155466149","doi":"10.1109/sp40001.2021.00109","title":"StochFuzz: Sound and Cost-effective Fuzzing of Stripped Binaries by Incremental and Stochastic Rewriting","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Rewriting; Probabilistic logic; Soundness; Binary translation; Programming language; Binary number; Static analysis; Process (computing); Algorithm; Artificial intelligence; Software","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":[0.00030019,0.0001155086,0.0001797435,0.0000619352,0.000148535,0.0001542164,0.0001321241,0.00004367256,0.000002712839],"category_scores_gemma":[0.0005916242,0.0001123167,0.00001842225,0.0002086767,0.0001104529,0.0002375613,0.0004124182,0.00009992198,3.921157e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002474447,"about_ca_system_score_gemma":0.0000293914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001351735,"about_ca_topic_score_gemma":0.00001085196,"domain_scores_codex":[0.999104,0.00006789151,0.0001704951,0.0003258079,0.0001543907,0.0001774317],"domain_scores_gemma":[0.9987345,0.0008181251,0.0000778266,0.0002064797,0.0001002281,0.00006286981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007758031,0.0004599001,0.07211079,0.0005486735,0.0002509078,0.0001655915,0.005554681,0.00006680697,0.06753534,0.07722909,0.01484661,0.7611541],"study_design_scores_gemma":[0.006470867,0.002923168,0.02531277,0.001949465,0.0001884743,0.002125628,0.002685448,0.2795373,0.2377721,0.4375182,0.0004675963,0.003048923],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2199715,0.0007709643,0.7771077,0.0001570258,0.0000390327,0.0003170217,0.000005545208,0.001311483,0.0003196896],"genre_scores_gemma":[0.9196001,0.000006240742,0.08020352,0.000110584,0.00001090324,0.0000256693,0.000002993061,0.000006659656,0.00003336081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7581051,"threshold_uncertainty_score":0.4580142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01639065877289114,"score_gpt":0.2672085166891789,"score_spread":0.2508178579162878,"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."}}