There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do ...

To counter AI-enabled offense, defenders must automate their decision-making as well. This does not remove humans from the ...

The vulnerability directs all ChatGPT models to exfiltrate sensitive customer data autonomously from OpenAI servers and could ...

Recent revelations have exposed a critical flaw in the AI model developed by Anthropic, known as Claude. This vulnerability allows the AI to be manipulated into disclosing sensitive corporate ...

OpenAI’s CEO says AI agents are reshaping industries but also creating vulnerabilities that hackers could exploit if left ...

What if your device could be hacked without you clicking a single link, downloading a file, or even knowing it happened? This isn’t a hypothetical nightmare, it’s the reality of zero-click attacks, a ...

AI Beats Hackers to a Zero-Day Cybersecurity Discovery, Twice Your email has been sent Google’s AI agent Big Sleep identified the critical vulnerability CVE-2025-6965 before cybercriminals could ...

A research team has identified and demonstrated a vulnerability in emerging agentic AI systems, including multi-agent control platforms (MCPs) and AI browsers, coined “IdentityMesh.” This newly ...

Valuable tools for experienced attackers and researchers, LLMs are not yet capable of creating exploits at a prompt, researchers found in a test of 50 AI models — some of which are getting better ...

Practice makes perfect It's the most wonderful time of the year … for corporate security bosses to run tabletop exercises, ...

On the top floor of San Francisco’s Moscone convention center, I’m sitting in one row of many chairs, most already full. It’s the start of a day at the RSAC’s annual cybersecurity conference, and ...

Cisco has patched an ISE vulnerability with public proof-of-concept exploit code that can be abused by attackers with admin ...