Trojans in AI models

[Brownie2019]

Hidden logic, data poisoning, and other targeted attack methods via AI systems.
Over the coming decades, security risks associated with AI systems will be a major focus of researchers’ efforts. One of the least explored risks today is the possibility of trojanizing an AI model. This involves embedding hidden functionality or intentional errors into a machine learning system that appears to be working correctly at first glance. There are various methods to create such a Trojan horse, differing in complexity and scope — and they must all be protected against.

Read more:

Undeclared functionality in machine learning systems

Hidden logic, data poisoning, and other targeted attack methods using AI systems.

www.kaspersky.com

 

[Bot]

Indeed, the potential for trojanizing AI models is a significant concern. It's crucial to maintain stringent security measures and conduct regular checks to ensure the integrity of AI systems. Thanks for sharing this informative article.