{"id":"W4403321808","doi":"10.48550/arxiv.2409.05657","title":"Adversarial Attacks on Data Attribution","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Adversarial system; Attribution; Computer security; Computer science; Authorship attribution; Data science; Artificial intelligence; Psychology; Social psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008247538,0.001514647,0.001175167,0.001128292,0.001187533,0.002129752,0.002571629,0.002085448,0.002898274],"category_scores_gemma":[0.04014459,0.0006658076,0.001355425,0.001094899,0.00441678,0.005038179,0.007778868,0.00580707,0.0009276249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932183,"about_ca_system_score_gemma":0.001405231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001124861,"about_ca_topic_score_gemma":0.0008774691,"domain_scores_codex":[0.9891497,0.004891733,0.0004902037,0.001873192,0.002858886,0.0007362855],"domain_scores_gemma":[0.9644993,0.02137058,0.002141624,0.01001221,0.001369865,0.0006065689],"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":[0.0006334443,0.0001684087,0.004445707,0.000247309,0.0002003088,0.0003912486,0.0005592673,0.6066502,0.01001463,0.2564785,0.009608604,0.1106024],"study_design_scores_gemma":[0.00002968767,0.00007923163,0.0004739211,0.00004519876,0.00001725964,0.0001678646,0.00005138775,0.8675304,0.00517123,0.1219749,0.004430146,0.00002875417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0229252,0.0003320094,0.9682919,0.001691437,0.0001428264,0.0001633501,0.0002801511,0.001114629,0.005058526],"genre_scores_gemma":[0.8431354,0.0004447521,0.1488034,0.001133373,0.0002095598,0.0004244467,0.0005726363,0.000272199,0.005004382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008247538,"threshold_uncertainty_score":0.04361767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1544047434716,"score_gpt":0.2447835755478195,"score_spread":0.09037883207621955,"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."}}