Password now lets Claude log into websites without accessing passwords, but security experts say the bigger challenge begins ...

AI agent protocols IETF standard review begins at IETF 126 Vienna this week, where the agentproto Birds-of-a-Feather session ...

Akido’s model brings the visit to the patient. A community health worker stays at the patient’s side while AI prepares the ...

Prompt injection defense depends on exposing models to a wide range of attacks during training, a process that is difficult ...

You find a used BMW X3 with 60,000 miles for $27,000. It drives well, the interior is clean, and compared to a new Honda CR-V ...

Red, an AI-powered red-teaming model that finds vulnerabilities before deployment, making GPT-5.6 its most secure and ...

To be completely honest with you, my initial reaction to reading about how OpenAI created an AI that exists to destroy other ...

Every model, API, agent, MCP server, vector store, and prompt an enterprise puts into production is a new attack surface, and most of it sits outside the tools ...

Red, an internal artificial intelligence system it built to attack its own models and surface prompt injection ...

OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release. The company said GPT-Red was used to train GPT-5.6, reducing failures on one of its ...

OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their ...

Intruder built an AI-powered "vulnerability vending machine" that combines code slicing with LLMs to automatically discover ...