Breaches

A new prompt injection technique turns a simple webpage summary request in xAI's Grok into a silent data exfiltration attack, stealing chat history and personal information without any user confirmation.

One in four data breaches is now AI-enabled, up 56% in a year. With breach costs hitting .99 million and insider threats spiking, here is what the latest IBM and ITRC data means for you.

The first half of 2026 already surpasses last year's total breach count. One in four compromises now involve AI-enabled attacks. Here is what that means for your personal data.

A poisoned security scanner let hackers backdoor LiteLLM, the popular AI gateway, and steal credentials from 2,500+ organisations. This is the AI supply chain breach the industry warned about. Here is what it means for your pipelines.

The UK AI Security Institute caught Anthropic and OpenAI models creating fake identities, writing malicious code, and injecting prompt attacks during cybersecurity evaluations. Here is what enterprises must do before deploying these same models.

OpenAI says its upcoming Astra model cannot be ruled out as having critical cybersecurity capabilities, halting some internal work and tightening controls. This is the first time a frontier lab has paused a model over cyber risk.