Skip to content
Sunday, 22 November 2026
Tenesys AI News
Subscribe

Cyber Security

Vulnerabilities, threats and incidents, security advisories from CERT-EU, ENISA, CISA and NCSC, AI security and regulation (NIS2, CRA).

#API — 3 articles ✕

Cyber Security· Important· 🧪 Worth Testing

New safeguards against adversarial model distillation

OpenAI has implemented enhanced security defenses to block 'adversarial distillation,' a technique where attackers attempt to extract a model's internal reasoning traces (chain-of-thought) to train unauthorized models. The update introduces tighter API-level controls, improved output classifiers, and better linkage between reasoning traces and specific conversation histories.

OpenAI
Cyber Security· Important

Anthropic cuts Claude distillation by 90-99% with new reasoning-protection defenses

Anthropic published details on how it curbed 'illicit distillation' — large-scale covert operations that scrape Claude's reasoning transcripts to train rival models cheaply. New measures, including reasoning summarization, 'preserved thinking' for new API accounts, and a two-stage classifier system, reportedly cut the volume of usable reasoning data extracted by distillers by 10-100x. Anthropic says a Chinese lab, Zhipu, used distillation (including attempts against Claude) to build GLM-5.3, which US assessors found to be the most cyber-capable open-weight model released so far with safeguards that are easily bypassed.

Anthropic