{"id":"W3168454669","doi":"10.1007/s10922-021-09608-6","title":"A Novel Lightweight Defense Method Against Adversarial Patches-Based Attacks on Automated Vehicle Make and Model Recognition Systems","year":2021,"lang":"en","type":"article","venue":"Journal of Network and Systems Management","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Adversarial system; Robustness (evolution); Overhead (engineering); Artificial intelligence; Computer security; Cyber-physical system; Convolutional neural network; Focus (optics); Deep learning; Situation awareness; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005995518,0.0006772598,0.0008555799,0.0005335448,0.0004624451,0.0006311057,0.0009607542,0.001070418,0.002005994],"category_scores_gemma":[0.002067164,0.000289491,0.0006061271,0.0003069932,0.0005652835,0.001205403,0.00194998,0.001351803,0.0007637831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003950745,"about_ca_system_score_gemma":0.0006441702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000695837,"about_ca_topic_score_gemma":0.0007901061,"domain_scores_codex":[0.9990985,0.000142467,0.00003318744,0.0001556275,0.0004163988,0.0001538188],"domain_scores_gemma":[0.9990091,0.0003119878,0.0001066946,0.000353111,0.000160835,0.00005816563],"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":[0.0007320052,0.0002447091,0.001988846,0.0001394244,0.0002003033,0.0004059662,0.0001283254,0.3394176,0.1128295,0.03859369,0.008880163,0.4964395],"study_design_scores_gemma":[0.00001137853,0.00008111312,0.000277242,0.000003929969,0.0000135401,0.0001207854,0.00000975753,0.9848764,0.008925819,0.004367547,0.001303005,0.000009428811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03662241,0.000234219,0.9585343,0.0002201199,0.0001266092,0.00006659624,0.00003677902,0.001772112,0.0023868],"genre_scores_gemma":[0.8650755,0.0001499205,0.1281594,0.0002205351,0.0001188265,0.00007416308,0.0001429698,0.000124005,0.005934603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002005994,"threshold_uncertainty_score":0.006710708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02913366341677486,"score_gpt":0.2757896375299138,"score_spread":0.2466559741131389,"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."}}