{"id":"W4409362363","doi":"10.1609/aaai.v39i25.34821","title":"Perception-Guided Jailbreak Against Text-to-Image Models","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Education and Child Care","funders":"Fundamental Research Funds for the Central Universities; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China; National Research Foundation Singapore; National Research Foundation","keywords":"Perception; Image (mathematics); Computer science; Psychology; Artificial intelligence; Cognitive psychology; Natural language processing; Neuroscience","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":[0.002935648,0.001203018,0.0009772377,0.0005881388,0.000695241,0.001228409,0.00171637,0.001504148,0.003264123],"category_scores_gemma":[0.01315755,0.0003618992,0.000733293,0.0002288499,0.002049548,0.002902602,0.003205993,0.003096388,0.001184567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007664505,"about_ca_system_score_gemma":0.0009044912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00095341,"about_ca_topic_score_gemma":0.001087502,"domain_scores_codex":[0.9979965,0.00068343,0.00008026991,0.0004129682,0.0005698526,0.0002569017],"domain_scores_gemma":[0.9925282,0.003897703,0.0009337112,0.001666111,0.0005944413,0.00037976],"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":[0.00376265,0.00105212,0.00763381,0.0006974345,0.0002582069,0.0009712862,0.001923734,0.4133468,0.09383372,0.05509788,0.02842369,0.3929987],"study_design_scores_gemma":[0.00006212306,0.0002750498,0.0004236944,0.00002107043,0.00001606322,0.0001786879,0.0001565373,0.9631468,0.01789726,0.01566453,0.002126428,0.00003175182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1940039,0.0006373829,0.7818087,0.001411692,0.0003541185,0.0003723049,0.0002275207,0.01426685,0.006917581],"genre_scores_gemma":[0.8928362,0.00008510341,0.1026582,0.000574037,0.0000680911,0.0001156152,0.0002490826,0.0005082079,0.002905417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003264123,"threshold_uncertainty_score":0.0155254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05902485939270401,"score_gpt":0.3197705640422241,"score_spread":0.2607457046495201,"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."}}