AI Guardrails Aren’t Stopping Criminal Hackers
Researchers from CrowdStrike identified four new criminal hacking groups using AI infrastructure, primarily older versions of Anthropic's Claude and Deepseek models, to conduct autonomous attacks. These groups exploited differences in AI guardrails and leveraged AI for speed and volume, rather than novel exploits, leaving their infrastructure openly accessible for analysis.
Why it matters
This highlights the growing threat of AI-powered cyberattacks, demonstrating that existing AI guardrails are insufficient and that even less sophisticated actors can leverage AI for widespread malicious activity, posing significant challenges for cybersecurity globally.
Researchers from the threat intelligence firm CrowdStrike looked at the AI infrastructure powering attacks perpetrated between May and August by four previously unreported groups—one that operates in Chinese, one in Spanish and English, one in Indonesian, and one in Russian. The former two exhibited sophisticated AI “harnesses,” the software that supports and guides a model to carry out tasks. The latter two showed less technical prowess, researchers found, but were still able to compromise multiple targets. All had left their AI infrastructure openly accessible on web servers, allowing the researchers to analyze their activity and which models they used—largely versions of Anthropic’s Claude as well as versions of the open-weight Deepseek models. All the actors devised ways to allow their campaigns to run autonomously over relatively long periods of time.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in