{"data":{"id":"3d1d0995-5c18-4400-be1d-1200db1272ed","title":"Combatting adversarial distillation","summary":"OpenAI describes a layered defense against adversarial distillation, in which an actor uses a frontier model's outputs without authorization to train a second model and deploy it without comparable safeguards. The company says it strengthened protections for protected reasoning, the intermediate chain-of-thought traces, in GPT-6.2 Astra and GPT-6.2 Sol. In an internal adaptive evaluation, the average attack success rate against recovering protected reasoning fell from 54.0% against GPT-6 Astra to 0.2% against GPT-6.2 Astra.","solution":"Strengthened defenses against protected reasoning extraction in GPT-6.2 Astra and GPT-6.2 Sol, with updated safeguards that align with those used for biology and cybersecurity. The approach combines adversarial testing, model training, classifiers, API-level protections, and investigations into coordinated extraction attempts.","labels":["security","safety"],"sourceUrl":"https://openai.com/index/combatting-adversarial-distillation","publishedAt":"2026-11-20T10:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_theft","data_extraction"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","GPT-6.2 Astra","GPT-6.2 Sol","GPT-6 Astra"],"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":"2026-11-20T10:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":null,"atlasIds":null}}