{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003053379,0.001061138,0.0004792324,0.0006027538,0.0004124032,0.001876352,0.00217302,0.001544281,0.01618989],"category_scores_gemma":[0.009520569,0.0003975078,0.0006142627,0.0004527671,0.001191703,0.002401817,0.002258882,0.003295603,0.00590467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008469243,"about_ca_system_score_gemma":0.0015321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006169158,"about_ca_topic_score_gemma":0.007046565,"domain_scores_codex":[0.9983681,0.0004389707,0.00008469023,0.0002275329,0.0007785043,0.0001021707],"domain_scores_gemma":[0.9947035,0.002477852,0.0003605307,0.001170262,0.001007407,0.0002804744],"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":[0.0004885507,0.0004677178,0.005049156,0.0004463024,0.0002127981,0.0008590239,0.0002889253,0.3378358,0.02259498,0.047459,0.2666809,0.317617],"study_design_scores_gemma":[0.00002631517,0.00008605469,0.0003684036,0.00003464868,0.00001011396,0.0001517708,0.00001562259,0.9529377,0.01061934,0.01008129,0.02564476,0.00002396703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0127236,0.0005504705,0.9127859,0.006052278,0.000651911,0.0003512962,0.002020257,0.04746812,0.01739611],"genre_scores_gemma":[0.4816212,0.001538925,0.4593794,0.005131233,0.0007183916,0.0006988363,0.007591147,0.005744708,0.03757603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01618989,"threshold_uncertainty_score":0.05416059,"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."}}