{"data":{"id":"3ed30af8-2477-42c2-b1ac-7996daa0f5fa","title":"Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models","summary":"Quality-Diversity Red-Teaming (QDRT) is a framework for automated red-teaming of large language models. It pursues diversity through behavior-conditioned training and an open-ended behavioral replay buffer, and trains multiple specialized attackers across attack styles and risk categories. The authors report that QDRT generates attacks that are more diverse and more effective against targets including GPT-2, Llama-3, Gemma-2, Qwen2.5, GPT-4.1 and GPT-5-Chat.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://doi.org/10.1162/evco.a.416","publishedAt":"2026-11-03T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Meta","Google"],"affectedVendorsRaw":["GPT-2","Llama-3","Gemma-2","Qwen2.5","GPT-4.1","GPT-5-Chat"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-03T00:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0054"]}}