{"data":{"id":"083e124d-948e-4d95-848b-dd2f96aa73eb","title":"Detecting Training Data For Large Language Models: A Survey","summary":"This survey article reviews methods for detecting training data used to build large language models (LLMs, which are AI systems trained on massive amounts of text to generate human-like responses). The paper examines various techniques that researchers have developed to identify and extract information about what data was used to train these models, which is important for understanding model behavior and potential privacy concerns.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://dl.acm.org/doi/abs/10.1145/3779430?af=R","publishedAt":"2026-03-16T21:11:52.638Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["data_extraction"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":"peer_reviewed","atlasIds":null}}