{"id":"W4393148469","doi":"10.1609/aaai.v38i6.28470","title":"FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; Agency for Defense Development; National Research Foundation of Korea; National Research Foundation","keywords":"Adversarial system; Computer science; Computer security; Artificial intelligence","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":[0.001828121,0.001064588,0.0006911851,0.0004756958,0.0003573101,0.000767747,0.001460942,0.001339998,0.002651681],"category_scores_gemma":[0.006124247,0.000313392,0.0005832966,0.0002498006,0.001724447,0.001757595,0.002870406,0.002605928,0.0006938748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006353598,"about_ca_system_score_gemma":0.0005199879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004000192,"about_ca_topic_score_gemma":0.0004633247,"domain_scores_codex":[0.9990407,0.0003136363,0.00003546386,0.0001811788,0.0003186456,0.0001103648],"domain_scores_gemma":[0.9980435,0.001025923,0.0001971633,0.0005203122,0.0001356313,0.00007745058],"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":[0.0004717226,0.0002213232,0.001573879,0.0001596786,0.0001301689,0.0002518014,0.0001050631,0.7079104,0.0482442,0.07897717,0.004358984,0.1575957],"study_design_scores_gemma":[0.00001757105,0.00009536045,0.0001385125,0.00001062747,0.000007578406,0.0000884493,0.000006469173,0.9704405,0.01087647,0.01712314,0.001183838,0.00001158038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02129756,0.0001961807,0.9740795,0.0003023798,0.00005511548,0.00007681638,0.00005194554,0.001388634,0.002551883],"genre_scores_gemma":[0.8316927,0.0001599386,0.1637962,0.0005045435,0.00006586901,0.00015442,0.0001361298,0.0002183554,0.003271923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002651681,"threshold_uncertainty_score":0.009668112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06289783033739495,"score_gpt":0.3213497346852908,"score_spread":0.2584519043478959,"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."}}