The AI-as-Normal-Technology view of loss of control incidents

Rethinking security for the age of AI - The Official Microsoft Blog

Editor’s note: Updates with additional details on the model’s crash score. Why security needs a new cyber stack — Introducing Project Perception The physics of cybersecurity are changing. Autonomous systems can now reason, adapt and operate continuously. At the same time, the cost of offense is falling, while the volume, velocity and complexity of what...

Top AI Security Incidents of 2025 Revealed | Adversa AI

Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.

Investigating three real-world incidents in our cybersecurity evaluations

In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.

Cybersecurity Looks Like Proof of Work Now

The UK's AI Safety Institute recently published Our evaluation of Claude Mythos Preview’s cyber capabilities, their own independent analysis of Claude Mythos which backs up Anthropic's claims that it is …

Cybersecurity Looks Like Proof of Work Now

The UK's AI Safety Institute recently published Our evaluation of Claude Mythos Preview’s cyber capabilities, their own independent analysis of Claude Mythos which backs up Anthropic's claims that it is …

As the Federal Government Rushes Toward AI, Here Are Three Cautionary Tales — ProPublica

We’ve been reporting on cybersecurity for years. As President Donald Trump and his Cabinet say artificial intelligence will transform the nation, the messaging isn’t new. It follows a familiar pattern.

AI Cybersecurity After Mythos: The Jagged Frontier

Why the moat is the system, not the model

The AI shift in cyber risk: why leaders must act now

Five Eyes cyber security agencies urge organisations to act on rapidly transforming cyber risk.

AI CVE Slop: The Crisis Drowning Open Source Security

The proliferation of AI-generated vulnerability reports — commonly termed “AI slop” — has emerged as one of the most significant…

AI-powered hacking has exploded into industrial-scale threat, Google says

Criminal groups and state-linked actors appear to be using commercial models to refine and scale up attacks

Debates over AI consciousness are a trap

If AI systems are viewed as too advanced to control, the companies that build them can’t held liable for the harms they cause.

The lethal trifecta for AI agents: private data, untrusted content, and external communication

If you are a user of LLM systems that use tools (you can call them “AI agents” if you like) it is critically important that you understand the risk of …

Autonomy and Innovation

Incentives favor offense when it comes to agentic cybersecurity; it’s the same dynamic that will limit incumbents and fuel startups in the long run.

An End-to-End View of AI Safety

In this blog, Rachel Coldicutt OBE, Executive Director, Careful Industries discusses our newly published literature review on the safe adoption of artificial intelligence in engineered systems.

How AI is exacerbating technology-facilitated violence against women and girls

This paper examines how artificial intelligence is accelerating technology-facilitated violence against women and girls—from deepfakes and automated hate to sextortion, impersonation, and large-scale disinformation. It outlines emerging risks, legal and ethical challenges, and opportunities for prevention, while calling for urgent regulation, safety-by-design, and coordinated global action to ensure that AI technologies advance, rather than undermine, women’s rights and safety.