{"id":"W4403577333","doi":"10.1145/3627673.3680102","title":"<scp>XploitSQL:</scp> Advancing Adversarial SQL Injection Attack Generation with Language Models and Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Web Application Security Vulnerabilities","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Adversarial system; Computer science; Reinforcement learning; SQL injection; SQL; Artificial intelligence; Programming language; World Wide Web; Query by Example","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":[],"consensus_categories":[],"category_scores_codex":[0.0003784773,0.0001405309,0.0001127228,0.000129806,0.0001821863,0.0004656072,0.0001617264,0.00005486811,0.00001105719],"category_scores_gemma":[0.00004262854,0.0001202736,0.00002564793,0.0003153917,0.00003334331,0.001565658,0.0001354518,0.000202348,0.00002893767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009628812,"about_ca_system_score_gemma":0.00007833059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001225419,"about_ca_topic_score_gemma":0.00006951982,"domain_scores_codex":[0.9987677,0.0000573582,0.0002015436,0.0004518713,0.0003012229,0.0002202986],"domain_scores_gemma":[0.999422,0.0001219107,0.00004643288,0.0002628565,0.00007153419,0.00007522703],"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":[0.000003403831,0.00001517753,0.00006884449,0.00008092044,0.00003300329,0.000007932344,0.02309216,0.7925115,0.008120041,0.1633321,0.002216364,0.01051852],"study_design_scores_gemma":[0.0001884746,0.0001365623,0.00001309128,0.00002239976,0.00000770773,0.00003346884,0.001441891,0.9870927,0.004981238,0.0005928733,0.005415557,0.00007397597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1753014,0.0002136984,0.8161714,0.0001677705,0.0001494041,0.0002156898,4.158048e-7,0.0004960649,0.007284098],"genre_scores_gemma":[0.9745901,0.00002491787,0.02132482,0.0001474544,0.0002336357,0.00005802921,0.00001302843,0.00001485923,0.003593167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7992887,"threshold_uncertainty_score":0.4904617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01930069543826017,"score_gpt":0.2600931777962212,"score_spread":0.2407924823579611,"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."}}