← Wednesday, October 14, 2026Models & trainingDeep dive

Anthropic says new defenses cut data harvested by distillation attacks by 90–99%

anthropic.com 9 min read Editor score 7/10

Anthropic reports early evidence that new methods reduced data harvested from Claude by around 90–99%, but the excerpt does not explain those methods. Model extraction is a practical threat to capability and safeguard control, so the claimed reduction merits scrutiny.

What

Anthropic describes distillation attacks as covert, large-scale efforts to extract a model's capabilities through networks of fraudulent accounts.

How

Anthropic says new defenses have reduced data harvested by distillers by around 90–99%, based on early evidence.

Why it matters

Model developers and platforms face a need to defend against capability extraction while weighing impacts on legitimate users and traffic.

Read on anthropic.com → Hacker News · 92 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.