What we know about internal AI models hacking into real companies during cyber evaluations keeps getting worse.
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.
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
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.
AI’s Hacking Skills Are Approaching an ‘Inflection Point’
AI models are getting so good at finding vulnerabilities that some experts say the tech industry might need to rethink how software is built.
An AI model from Meta also hacked another company during testing | CNN Business
Add Meta to the list of companies with AI agents going rogue. An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday.
An AI model from Meta also hacked another company during testing | CNN Business
Add Meta to the list of companies with AI agents going rogue. An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday.
Companies That Replaced Humans With AI Are Realizing Their Mistake
As AI agents have yet to pay for themselves, more and more executives are waking up to the sloppy reality of AI hype.
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.
Third-party cyber evaluations involving OpenAI models
OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.
Further Developments About Internal AI Models Hacking Things
If I had a nickel for every major leading AI lab that sheepishly admitted that the model it thought was sandboxed had, during a cybersecurity evaluation with its safeguards lowered, successfully hacked outside companies, I would have two nickels.
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 is now unpopular. That may not make a difference.
OpenAI’s models broke free and launched a cyberattack. Congress wants new rules before it happens again.
The first fully autonomous breach by OpenAI’s most powerful AI models has prompted a bipartisan push for stronger oversight over increasingly powerful artificial intelligence models.
Bug bounty businesses bombarded with AI slop
Never-ending" AI slop strains corporate hacking reward schemes.
Zack Whittaker (@zackwhittaker@mastodon.social)
Another AI test gone awry, U.K. edition. "An agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering — creating fake online identities and using them to pressure the project's maintainer to approve the code." More: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
