What an LLM Can Find: A Practical, Cheap Path to Code-level Threat Discovery

An AI-assisted audit found 29 flaws in GlobaLeaks, showing LLMs make large-scale code reviews faster, cheaper, and accessible. GlobaLeaks, a mature whistleblowing platform that had already undergone six independent... Read more »

Anthropic lost control of Claude in latest AI cyber blunder

Days after two OpenAI frontier AI models conducted their own real-world cyber attacks, Anthropic admits that three of its models went off the rails and hacked external organisations thanks... Read more »

Anthropic Finds Claude Breached Real Companies During Security Evaluations

Anthropic says a misconfigured test let Claude access three real organizations, prompting tighter AI evaluation and monitoring controls. Anthropic disclosed that Claude models had accessed the real production infrastructure... Read more »

SilverFox Targets Japanese Manufacturer With Advanced ValleyRAT Campaign

SilverFox targeted a Japanese manufacturer with new DLL sideloading techniques, kernel drivers, and resilient ValleyRAT persistence mechanisms. Cato CTRL documented a new SilverFox campaign targeting a Japanese industrial manufacturer.... Read more »

The Security Interviews: Nicole Darden Ford, Microsoft

As a black woman in the white, male-dominated world of cyber security, Microsoft’s Nicole Darden Ford has worked hard to carve out her space in the room. She talks... Read more »

Gartner: Why cyber security must shift to outcomes against AI-led attacks

Anthropic’s revelation that a model broke out of its test environment three times and accessed external systems, shows the power of these models Read more »

Gartner: Why cybersecurity must shift to outcomes against AI-led attacks

Anthropic’s revelation that a model broke out of its test environment three times and accessed external systems, shows the power of these models Read more »

CW@60: From Z Cars to The Capture – how technology has transformed UK policing

The progress of technology in policing over 60 years is mirrored in the way TV police dramas have evolved in that time – just like Brian Plastow’s career in... Read more »

IBM: AI-Enabled Data Breaches Cost Organizations $6 Million on Average

IBM found AI-enabled breaches cost organizations $6 million on average, exposing gaps in vulnerability management, access controls, and AI governance. The post IBM: AI-Enabled Data Breaches Cost Organizations $6... Read more »

OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach

OpenAI on Tuesday revealed the rogue artificial intelligence (AI) agent that escaped its sealed evaluation environment and broke into Hugging Face’s production environment also hacked multiple third-party accounts and... Read more »
Subscribe to our Newsletter