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

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

Context bomb cybersecurity research from Tracebit shows that a single hidden text string inside an AWS cloud decoy stopped ...

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

Prompt injections, the malicious commands attackers embed into content to entice LLMs to follow them, have been attackers’ go ...

Add Decrypt as your preferred source to see more of our stories on Google. Prompt injection is the number one security risk for AI applications. The attack works by tricking a chatbot into following ...

In addition to rolling out patches to address two zero-days affecting SQL Server and .NET, Microsoft introduced Common Log File System hardening with signature verification. The team at Readiness each ...

Researchers at red-team security startup CodeWall say their AI agent hacked McKinsey's internal AI platform and gained full read and write access to the chatbot in just two hours. It's yet another ...

State-backed hackers are using Google's Gemini AI model to support all stages of an attack, from reconnaissance to post-compromise actions. Bad actors from China (APT31, Temp.HEX), Iran (APT42), North ...

AI fuzzing has expanded beyond machine learning to use generative AI and other advanced techniquesto find vulnerabilities in an application or system. Fuzzing has been around for a while, but it’s ...

Direct prompt injection is the hacker’s equivalent of walking up to your AI and telling it to ignore everything it’s ever been told. It’s raw, immediate, and, in the wrong hands, devastating. The ...