Get the latest Science News and Discoveries

Hacking AI Agents—How Malicious Images and Pixel Manipulation Threaten Cybersecurity


Artificial-intelligence agents—touted as AI’s next wave—could be vulnerable to malicious code hidden in innocent-looking images on your computer screen

None

Get the Android app

Or read this on Scientific American

Read more on:

Photo of agents

agents

Photo of pixel manipulation

pixel manipulation

Photo of malicious images

malicious images

Related news:

News photo

AI's Third Phase Is Here. Here's How 'Agents' May Impact Our Lives.

News photo

An extension of process calculus for asynchronous communications between agents with epistemic states - EurekAlert

News photo

Inducing agents for Alzheimer’s disease in animal models - EurekAlert