{"id":"W4386162746","doi":"10.1145/3617502","title":"Black-box Attack against Self-supervised Video Object Segmentation Models with Contrastive Loss","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Computer science; Artificial intelligence; Black box; Feature (linguistics); Adversarial system; Object (grammar); Deep learning; Metric (unit); Focus (optics); Frame (networking); Pattern recognition (psychology); Pixel; Machine learning; Computer vision","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":[0.002084267,0.001032519,0.0008542691,0.0004614609,0.0003928487,0.0007158748,0.001246583,0.00150235,0.001128964],"category_scores_gemma":[0.006060985,0.0003694318,0.0009200882,0.0002662049,0.001492969,0.001731583,0.002029144,0.002449918,0.0003959211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001312382,"about_ca_system_score_gemma":0.000872149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002369659,"about_ca_topic_score_gemma":0.002591704,"domain_scores_codex":[0.9985669,0.0004453293,0.00006091044,0.000308807,0.0004416547,0.0001764012],"domain_scores_gemma":[0.9971066,0.00152428,0.0003297575,0.0007088188,0.0002265033,0.0001039738],"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":[0.0007031969,0.0001743332,0.002506822,0.00009624167,0.0001690952,0.000306618,0.0002170617,0.8350874,0.02881419,0.01829795,0.003948967,0.1096781],"study_design_scores_gemma":[0.000007208418,0.00005869113,0.000185089,0.000005733087,0.000004628931,0.00005148567,0.000007504545,0.9896998,0.006775035,0.002823082,0.0003756592,0.000006024462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1943278,0.0005398956,0.7964215,0.0009044887,0.0001297262,0.0001315204,0.0001558743,0.003426685,0.003962499],"genre_scores_gemma":[0.9125397,0.0001290844,0.08444658,0.0003509164,0.00003493779,0.00007560472,0.00019004,0.0001672722,0.002065904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002369659,"threshold_uncertainty_score":0.01102281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02862455122646619,"score_gpt":0.2963149242982362,"score_spread":0.2676903730717701,"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."}}