OpenAI’s New Red-Teaming Weapon OpenAI has pulled back the curtain on GPT-Red, an internal automated red-teaming model designed to scale prompt injection vulnerability discovery. The goal?...
The Short Version: A Stolen Certificate Opens Every Door Pull the certificate off the flash of a Shark RV2320EDUS robot vacuum, and you can run root...
The Day a Benchmark Became a Breach On a seemingly ordinary weekend, something unprecedented happened in the world of AI security. An OpenAI model, tasked with...
The Speed of AI vs. The Standard of Proof Artificial intelligence is reshaping offensive security. Tools powered by machine learning can now skim thousands of lines...
When a Single Request Isn’t Enough A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source...
A Record-Breaking Year for Patch Tuesday Microsoft’s August Patch Tuesday is here, and it’s a big one. The company has released fixes for at least 398...
A $36 Million Bet on AI-Driven Email Defense Email security startup AegisAI has secured $36 million in a Series A round led by Battery Ventures, with...
USB Auto-Install: The Unexpected Attack Surface Plugging in a USB stick feels routine. You expect a quick notification and maybe a driver install. But a team...
Daxin Rootkit Comes Back From the Dead A nasty piece of malware that most security teams probably thought was history has just popped up again. Daxin...
Urgent Patch Alert for Check Point Customers Check Point has confirmed that a critical zero-day vulnerability in its Security Management and Multi-Domain Management products is being...