{"id":"W4409364009","doi":"10.1609/aaai.v39i17.33927","title":"COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic Attacks","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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Defense Advanced Research Projects Agency; Nuclear Safety and Security Commission; National Aeronautics and Space Administration; National Science Foundation","keywords":"Commit; Robustness (evolution); Computer science; Fusion; Sensor fusion; Computer security; Artificial intelligence; Chemistry; Database; Philosophy","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009008119,0.0003296227,0.0005748445,0.0003251024,0.0003551695,0.000250269,0.003072376,0.0001742593,0.00001257036],"category_scores_gemma":[0.001026492,0.0002614718,0.0001796087,0.001319646,0.0003653355,0.0004270551,0.001098217,0.0005833497,0.00001652334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000862822,"about_ca_system_score_gemma":0.000149586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001019499,"about_ca_topic_score_gemma":0.00001024596,"domain_scores_codex":[0.9972191,0.00007539806,0.001009306,0.000640829,0.0006178186,0.0004374762],"domain_scores_gemma":[0.9971718,0.0002764003,0.0008210397,0.0005766932,0.001077667,0.00007637141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001184338,0.0003747324,0.002801595,0.0007655763,0.00007217059,0.000001715984,0.001680678,0.1532414,0.07094132,0.7034424,0.0001156388,0.06644437],"study_design_scores_gemma":[0.00007297305,0.00006039083,0.0003824408,0.001373888,0.000024368,0.000002277056,0.0010851,0.8871174,0.1073279,0.002271853,0.00004356334,0.000237888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.260096,0.00008823021,0.7295823,0.002212163,0.002228355,0.0008401427,0.000004234603,0.0001850148,0.004763626],"genre_scores_gemma":[0.9906232,0.00003763885,0.008752127,0.00007954988,0.00005940341,0.00002219984,5.861838e-7,0.00001716865,0.0004081173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.733876,"threshold_uncertainty_score":0.9999837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08277057206455064,"score_gpt":0.3241061842532059,"score_spread":0.2413356121886552,"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."}}