# Anthropic details new defenses that cut Claude reasoning extraction by distillers

> Original title: Strengthening our defenses against distillation attacks

- Source: Anthropic Newsroom
- Published: 2026-10-12T04:00:00.000Z
- Bad Influence: https://badinfluence.news/items/qwbce893bi49cwq54xv7hjfz5
- Original: https://www.anthropic.com/news/distillation-defenses

## Summary

Anthropic says its new defenses against distillation attacks cut the reasoning data harvested by distillers by around 90 to 99%. The methods include controlling where reasoning can go, a two-stage classifier that blocks extraction attempts, and making repeated attempts harder through stricter limits and bans. Anthropic says these measures reduced extracted reasoning tokens by 10 to 100 times on its own platform, but they require some developers to update integrations and can misidentify fewer than 0.1% of benign requests.

## Why it matters

The post explains concrete defenses against distillation, with reported extraction reductions and the trade-offs they carry for legitimate users.