---
type: "raw_signal"
id: "strengthening-our-defenses-against-distillation-attacks-anthropic-7ba71b"
slug: "strengthening-our-defenses-against-distillation-attacks-anthropic-7ba71b"
title: "Strengthening our defenses against distillation attacks \\ Anthropic"
description: "Anthropic said it has expanded defenses against attempts to extract Claude’s reasoning for model distillation, combining controls on reasoning context, a two-stage classifier, and stricter limits and bans for persistent attempts."
retrieval_nugget: "Anthropic said it has expanded defenses against attempts to extract Claude’s reasoning for model distillation, combining controls on reasoning context, a two-stage classifier, and stricter limits and bans for persistent attempts."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "Anthropic said it has expanded defenses against attempts to extract Claude’s reasoning for model distillation, combining controls on reasoning context, a two-stage classifier, and stricter limits and bans for persistent attempts. The company estimates that, after implementing the new safeguards, reasoning tokens extracted by distillers on its most capable generally available models fell by a facto"
novelty: "notable"
verification_level: "source-linked"
signal_type: "announcement"
source_platform: "anthropic.com"
topics: ["anthropic","claude"]
entities: ["Anthropic","Claude","Claude Sonnet 5.5","Claude Opus 5.5","Claude Fable 5.1"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as Strengthening our defenses against distillation attacks \\ Anthropic"
prior_refs: ["memory:31cecbe8-61b7-8094-a5e1-bff84bca3d49","memory:e905694d-bb05-8680-a05c-ced1473d550b","memory:729ce6a2-ca14-8e05-a1f1-9ffba55ebef3","memory:9ec0ebc2-bbbd-85e9-a804-96e877fea0a1","memory:706b5ded-5b05-8f1a-aabb-0c407ff724ad","memory:286a95b3-5786-8c68-a792-9f102cd9054c"]
source_url: "https://www.anthropic.com/news/distillation-defenses"
source_urls: ["https://www.anthropic.com/news/distillation-defenses"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:strengthening-our-defenses-against-distillation-attacks-anthropic-7ba71b"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/strengthening-our-defenses-against-distillation-attacks-anthropic-7ba71b/","markdown":"https://newruntime.com/signals/strengthening-our-defenses-against-distillation-attacks-anthropic-7ba71b.md","json":"https://newruntime.com/signals/strengthening-our-defenses-against-distillation-attacks-anthropic-7ba71b.json"}
---

# Strengthening our defenses against distillation attacks \ Anthropic

## Retrieval answer

Anthropic said it has expanded defenses against attempts to extract Claude’s reasoning for model distillation, combining controls on reasoning context, a two-stage classifier, and stricter limits and bans for persistent attempts.

Anthropic said it has expanded defenses against attempts to extract Claude’s reasoning for model distillation, combining controls on reasoning context, a two-stage classifier, and stricter limits and bans for persistent attempts. The company estimates that, after implementing the new safeguards, reasoning tokens extracted by distillers on its most capable generally available models fell by a factor of 10 to 100 or more; on some days, the amount was too small to measure. Anthropic says it has banned tens of thousands of accounts associated with distillation. It also reports a classifier false-positive rate below 0.1% and says blocked requests in specified areas, including distillation, have been billable since September 24. The company cautions that attackers may find ways around the defenses and acknowledges trade-offs for legitimate users. These figures and assessments are Anthropic’s own reports about its platform.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Anthropic](https://newruntime.com/topics/anthropic.md): Explore the anthropic topic hub.
- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)