{"slug": "openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models", "title": "OpenAI makes it much harder for attackers to extract how its latest AI models think", "summary": "OpenAI cut the success rate of attempts to extract protected internal reasoning from its GPT-6.2 Astra and GPT-6.2 Sol models from 54 percent to 0.2 percent in adaptive red-teaming tests, The Decoder reported. OpenAI also said it suspends thousands to tens of thousands of accounts each week over coordinated distillation campaigns.", "body_md": "OpenAI has significantly strengthened safeguards against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol. In adaptive red-teaming tests, the success rate for extracting protected reasoning fell from 54 percent to 0.2 percent. The company is also suspending thousands to tens of thousands of accounts each week over coordinated distillation campaigns.\n\nThe article [OpenAI makes it much harder for attackers to extract how its latest AI models think](https://the-decoder.com/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models-think/) appeared first on [The Decoder](https://the-decoder.com).", "url": "https://wpnews.pro/news/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models", "canonical_source": "https://the-decoder.com/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models-think/", "published_at": "2026-11-20 20:31:50+00:00", "updated_at": "2026-11-20 21:14:37.476102+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "artificial-intelligence"], "entities": ["OpenAI", "GPT-6.2 Astra", "GPT-6.2 Sol", "The Decoder"], "also_reported_by": [], "takeaway": "OpenAI's adaptive red-teaming cut protected-reasoning extraction success from 54 percent to 0.2 percent on GPT-6.2 Astra and GPT-6.2 Sol, and it suspends thousands to tens of thousands of accounts weekly for coordinated distillation campaigns.", "recommendation": {"advice": "Red-team your models adaptively for reasoning-extraction attacks and monitor for coordinated distillation campaigns; OpenAI's adaptive testing cut extraction success from 54 percent to 0.2 percent.", "playbook": "agent-security", "playbook_url": "https://wpnews.pro/playbooks/agent-security"}, "alternates": {"html": "https://wpnews.pro/news/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models", "markdown": "https://wpnews.pro/news/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models.md", "text": "https://wpnews.pro/news/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models.txt", "jsonld": "https://wpnews.pro/news/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models.jsonld"}}