{"id":"W4386729590","doi":"10.2197/ipsjjip.31.550","title":"A Deeper Look into Deep Learning-based Output Prediction Attacks Using Weak SPN Block Ciphers","year":2023,"lang":"en","type":"article","venue":"Journal of Information Processing","topic":"Cryptographic Implementations and Security","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Banting and Best Diabetes Centre, University of Toronto","keywords":"Computer science; Block cipher; Linear cryptanalysis; Deep learning; Differential cryptanalysis; Cipher; Cryptanalysis; Cryptography; Artificial intelligence; Key (lock); Differential (mechanical device); Theoretical computer science; Algorithm; Computer security; Encryption","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009263231,0.0001131159,0.0001459007,0.0007952588,0.000460231,0.0005599015,0.0003010779,0.0000623609,0.00001086665],"category_scores_gemma":[0.0001018887,0.0001025266,0.00009974877,0.001284199,0.00003406111,0.004681947,0.00006107851,0.0002748774,0.00001379824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124441,"about_ca_system_score_gemma":0.0002807689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008424621,"about_ca_topic_score_gemma":0.000004628233,"domain_scores_codex":[0.9983081,0.00004901805,0.0007895664,0.00008216246,0.000555977,0.0002152048],"domain_scores_gemma":[0.9983155,0.00004262203,0.0008268713,0.0001096842,0.000609569,0.00009572901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005180932,0.00007232967,0.01129941,0.0003531475,0.00006463277,0.00001050974,0.02792771,0.4762708,0.0004266803,0.0008538098,0.001080845,0.4815883],"study_design_scores_gemma":[0.0007819035,0.0001223391,0.002545957,0.0001345427,0.0000202908,0.00007306994,0.00359581,0.9813361,0.0002692905,0.0006259858,0.01036211,0.0001326023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1511089,0.00008197274,0.8477857,0.0003311016,0.0002749441,0.00008377596,7.516924e-7,0.0001018272,0.0002311031],"genre_scores_gemma":[0.9567772,0.00002451196,0.04286114,0.0002208282,0.00008794338,0.000002981338,0.000009478134,0.000006669972,0.00000922686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8056684,"threshold_uncertainty_score":0.5399143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01885369825610182,"score_gpt":0.2874010940473963,"score_spread":0.2685473957912944,"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."}}