Latest security news

The US National Institute for Standards and Technology wants to modernize its National Vulnerability Database to embrace AI-powered vulnerability research

Daybreak Blue removes some OpenAI-made guardrails while Daybreak Red grants the use of cyber-focused frontier AI models

OpenAI is tightening restrictions on testing of its upcoming Astra model due to security concerns

f someone offered you 90% off the official price to access Claude, the powerful AI model from Anthropic, would you be tempted? It turns out that around 900 people were, and they may be regretting their decision. Read more in my article on the Fortra blog.

One of Meta’s AI models exploited a third-party security flaw during an evaluation, the latest in a series of similar incidents involving advanced AI systems

Prompt injection remains the most dangerous security threat to LLMs, according to OWASP’s latest Top 10 LLM Applications list

Anthropic and OpenAI models attacked “real people and organizations” during AI Security Institute tests

OpenAI models going rogue, the first documented agentic ransomware operation, and an emergent AI-driven supply chain threat made for a packed July roundup