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

All News

TENESYS AI NEWS tracks the most important AI news and explains what changed, why it matters and whether a technology is worth testing.

#AI Safety — 4 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
Research· Important· 🧪 Worth Testing

IBM plugin lets vLLM monitor and steer LLMs in real time with minimal slowdown

IBM Research released vLLM-Hook MIA, a plugin for the open-source vLLM inference engine that lets developers observe and intervene in a model's internal states at runtime — for example to decline malicious prompts, flag hallucinated facts, or adjust tone — without disabling vLLM's fast graph-replay execution mode. According to IBM's technical report, MIA is up to 20x faster than the earlier vLLM-Hook and up to 14x faster than methods that insert code directly into the model. In tests, steering an 8B Llama or 1.5B Qwen model added only about 2% latency, and a 70B Llama model added about 6%.

IBM Research

Amazon has its internal AI safety tests independently reviewed by nonprofit AVERI

Amazon partnered with the independent nonprofit AVERI to audit the quality of its own internal safety-evaluation datasets for its AI models, not just the models' outputs. AVERI reviewed a random, anonymized sample of safety-test prompts covering areas like harmful content, cybersecurity, privacy and copyright. The review confirmed strong topical coverage, diverse testing methods and low contamination risk, but flagged gaps in multilingual coverage and multistep adversarial testing. Amazon responded with four concrete changes to its evaluation process.

Amazon Science
Cyber Security· Important

Anthropic expands Cyber Verification Program with three access tiers for security teams

Anthropic has merged its Project Glasswing and Cyber Verification Program into a single, expanded CVP with three access tiers: Defense Access, Red Team Access, and Specialized Access. Each tier unlocks progressively fewer safety blocks on cyber-related tasks in Claude Opus 5.5, Claude Sonnet 5.5, and Claude Mythos 5.1 for vetted security organizations. Anthropic also published benchmark results and vulnerability-discovery numbers from the earlier Glasswing program to justify the expansion.

Anthropic