Anthropic unveils Claude defenses reducing distillation attacks up to 99%
Anthropic (latest)en
Anthropic (latest)
AI Global WireAnthropic announced that its new security measures have reduced data extraction in distillation attacks on its Claude AI models by 90% to 99%.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Anthropic (latest) — open it there to read it in full.
Read the full story at Anthropic (latest)- Anthropic
Related AI news
- HCLTech, Anthropic partner on enterprise AI agentsTech in Asia · October 13, 2026
- Anthropic says new measures like preserved thinking in Fable 5.1 and Opus 5.5 have reduced data harvesting through distillation attacks by about 90% to 99% (Anthropic)Techmeme · October 13, 2026
- NTT Data in final talks to build Anthropic's first data centre in Japan, Nikkei reportsEconomic Times Tech · October 13, 2026
- Anthropic 也要培訓「前線部署工程師」，目標訓練萬名「AI 傳教士」將 Claude 切實導入企業經營TechNews (TW) · October 13, 2026
- Sources: NTT Data is in advanced talks to build a data center for Anthropic in Osaka of up to 500 MW, among Japan's largest, potentially costing $6.3B (Nikkei Asia)Techmeme · October 13, 2026
- Meta launches Muse Wonder to rival OpenAI, AnthropicTech in Asia · October 13, 2026