Anthropic says new defenses cut distillation data harvested from Claude by 90 to 99 percent

What happened

Anthropic says new defenses cut distillation data harvested from Claude by 90 to 99 percent, according to Crypto Briefing. Enhanced defenses against distillation attacks bolster AI security, ensuring model integrity and safeguarding proprietary technology advancements. 12, 2026 Anthropic says it has made serious headway against people trying to copy Claude’s homework. Anthropic is an artificial intelligence company based in San Francisco, and its products and services include Claude and Claude Code.

According to the company, new defenses have cut the amount of data harvested through distillation attacks by 90 to 99 percent . The figures come from a September 2026 threat intelligence report.

In it, Anthropic details how it has tracked, attributed and disrupted illicit attempts to extract Claude’s capabilities. The focus falls mainly on reasoning, coding and tool use.

Nearly 200 million exchanges, one very large customer Technically, a rival collects large volumes of a stronger model’s responses and operates with those transcripts as training data (the material a model is built from). Anthropic says it attributed nearly 200 million distillation-related exchanges across five separate campaigns in its latest report.

The biggest of the five stands out. Anthropic linked it to Alibaba’s Qwen, and it involved more than 151 million exchanges between May and July 2026. Advertisement This is not the first time Anthropic has gone public on the issue.