OpenAI develops automated attacker system to test ChatGPT Atlas browser security against prompt injection threats and ...

Security researchers from Radware have demonstrated techniques to exploit ChatGPT connections to third-party apps to turn ...

From data poisoning to prompt injection, threats against enterprise AI applications and foundations are beginning to move ...

While the shortest distance between two points is a straight line, a straight-line attack on a large language model isn't always the most efficient — and least noisy — way to get the LLM to do bad ...

That's according to researchers from Radware, who have created a new exploit chain it calls "ZombieAgent," which demonstrates ...

OpenAI's new GPT-4V release supports image uploads — creating a whole new attack vector making large language models (LLMs) vulnerable to multimodal injection image attacks. Attackers can embed ...

Recently, OpenAI extended ChatGPT’s capabilities with user-oriented new features, such as ‘Connectors,’ which allows the ...

Researchers from Princeton University warn of AI agents with “underexplored security risks” in a recently published paper. Dubbed 'Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks ...

For a brief moment, hiding prompt injections in HTML, CSS, or metadata felt like a throwback to the clever tricks of early black hat SEO. Invisible keywords, stealth links, and JavaScript cloaking ...

Here we go again. While Google’s procession of critical security fixes and zero-day warnings makes headlines, the bigger threat to its 3 billion users is hiding undercover. There’s “a new class of ...

Although you might not have heard of the term, an agentic AI security team is one that seeks to automate the process of detecting and responding to threats by using intelligent AI agents. I mention ...