Security

New prompt-based technique to enhance AI security

Researchers have developed a new approach to AI security that employs text prompts to better protect AI systems from cyber threats. This method focuses on the creation of adversarial examples to prevent AI from being misled ...

Machine learning & AI

AI's mysterious 'black box' may not be so black

One of the pioneers of Explainable AI has developed an advanced model that explains how and why AI works. The model opens up AI's mysterious "black box" and is available for virtually all AI systems.

page 1 from 10