Anthropic says new safeguards sharply reduce AI distillation attacks

Oct 12 (Reuters) - Anthropic ‌said on Monday ​new ​measures designed to prevent rivals from copying the capabilities of its Claude AI models ‌have reduced data harvested in so-called distillation attacks by ⁠about 90% to 99%.

• Model distillation has emerged as a ‌key concern for leading AI ‌companies due to intensifying US-China competition, with firms including Anthropic, OpenAI and Google arguing the practice enables ​rivals to reproduce advanced capabilities more quickly and at lower cost

• Anthropic said safeguards restricting access ⁠to Claude's reasoning have sharply reduced extraction attempts, with "the number of reasoning tokens ​extracted by distillers" now "10 to 100 times lower than it was before"

• The California-headquartered company ​said it had made it ‌harder to use proxy networks to repeatedly probe Claude's protected reasoning, blocking extraction attempts ⁠and hindering large-scale distillation efforts

• Anthropic said its safety system is "roughly as robust as those that prevent Claude from helping ⁠build bioweapons" and has "a false positive rate of less than 0.1%"

• ​Anthropic banned tens of thousands of accounts linked to distillation campaigns and cited Chinese AI startup Z.ai, also known as Zhipu, ‌as an example of a company that attempted to distill capabilities from Claude while ‌developing its GLM-5.3 model, warning such practices pose safety ⁠and national security risks

• ‌Z.AI did not immediately ​respond to a request for comment

(Reporting by Mrinmay Dey in Mexico City; Editing by Sherry ‌Jacob-Phillips)

---

Serious News for Serious Traders! Try StreetInsider.com Premium Free!

---

You May Also Be Interested In

• 88.6% of Japan households expect prices to rise a year from now, BOJ says
• ASEAN foreign ministers to tackle transboundary haze in November meetings
• South Korea says US raises intelligence cooperation concerns, Yonhap says