{"id":"W2179402106","doi":"10.48550/arxiv.1511.05122","title":"Adversarial Manipulation of Deep Representations","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Adversarial system; Image (mathematics); Artificial intelligence; Representation (politics); Computer science; Class (philosophy); Natural (archaeology); Similarity (geometry); Pattern recognition (psychology); Space (punctuation); Computer vision; Geography","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":[0.0006308216,0.00071322,0.0003215263,0.000286519,0.000273759,0.0006047871,0.000820925,0.0007491519,0.002241328],"category_scores_gemma":[0.00384036,0.0002442356,0.0004110332,0.0001986811,0.001533796,0.001369049,0.001872714,0.001718807,0.0003355977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005739213,"about_ca_system_score_gemma":0.0003137669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006635921,"about_ca_topic_score_gemma":0.000557992,"domain_scores_codex":[0.999519,0.000140374,0.00001502677,0.000100443,0.000149183,0.00007597798],"domain_scores_gemma":[0.9988946,0.0005646885,0.0001442084,0.0002912383,0.00005748029,0.0000477793],"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":[0.000194726,0.0000570013,0.0007636428,0.00007682663,0.00006338913,0.0003275269,0.0001177631,0.7280047,0.03316886,0.2058456,0.002931645,0.02844835],"study_design_scores_gemma":[0.000009306393,0.00003985906,0.0002008888,0.00001450924,0.000007288583,0.00008621133,0.00001620031,0.9329415,0.007019494,0.05759827,0.002056529,0.00001001313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08475316,0.0002417537,0.8978145,0.0008767948,0.0001242863,0.00004483499,0.0001641783,0.0004924341,0.01548812],"genre_scores_gemma":[0.9476651,0.0002142268,0.04710599,0.0002847941,0.00004555488,0.0000596597,0.0001214841,0.00009163123,0.004411721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002241328,"threshold_uncertainty_score":0.007497966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09478518249713105,"score_gpt":0.2336188496903275,"score_spread":0.1388336671931964,"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."}}