{"data":{"id":"4726266d-a382-4cdf-b351-e183e4dc6900","title":"Improving Fuzzy Robustness in LLM Safety with Automated Red Teaming","summary":"OpenAI describes how automated red-teaming was used to train GPT-6 Astra and Sol to resist jailbreaks in high-stakes domains such as cyber, biology and violent activity. An attacker model iteratively refines prompts against defender models GPT-5.4 and GPT-5.5, and the resulting synthetic jailbreaks serve as training data. On a fixed cyber jailbreak dataset, GPT-6 Astra answered 91.5% safely versus 59% for GPT-5.6 Sol, measured without production safeguards.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://alignment.openai.com/fuzzy-robustness/","publishedAt":"2026-11-12T08:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["GPT-6 Astra","GPT-6 Sol","GPT-5.4","GPT-5.5","GPT-5.6 Sol","GPT-Red","OpenAI Daybreak","OpenAI Rosalind"],"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":"2026-11-12T08:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"industry","atlasIds":["AML.T0054"]}}