Offensive security startup Armadin secured nearly $190 million in funding to expand a platform that uses AI agents to automate red-team operations. The technology ...

OpenAI has taken a more aggressive approach to red teaming than its AI competitors, demonstrating its security teams' advanced capabilities in two areas: multi-step reinforcement and external red ...

OpenAI acquires Promptfoo to embed AI red-teaming and security testing directly into its Frontier agent platform, signaling that agent safety is now table stakes.

Red teaming is a powerful way to uncover critical security gaps by simulating real-world adversary behaviors. However, in practice, traditional red team engagements are hard to scale. Usually relying ...

Unrelenting, persistent attacks on frontier models make them fail, with the patterns of failure varying by model and developer. Red teaming shows that it’s not the sophisticated, complex attacks that ...

The acquisition points to rising demand for tools that test and secure LLMs before they are deployed in enterprise workflows.

Nearly every organization today works with digital data—including sensitive personal data—and with hackers’ tactics becoming more numerous and complex, ensuring your cybersecurity defenses are as ...

A tool for red-team operations called EDRSilencer has been observed in malicious incidents attempting to identify security tools and mute their alerts to management consoles. Researchers at ...