Tag: AI Security
Google’s Fairwind Program Gates Its Least-Restricted Cyber Model
Google launched Fairwind on September 2, 2026: vetted partners get Gemini 3.8 Flash Cyber — the variant that ships with deliberately looser safety mitigations.
Perplexity BrowseSafe: Safer AI Browsers
Perplexity introduces BrowseSafe, an open detection model and benchmark for protecting AI agents from prompt injection attacks in browser environments.
Anthropic: 250 Malicious Docs Can Poison Any LLM
Anthropic publishes research on data poisoning, proposing new defense mechanisms to protect large language models from adversarial training data attacks.