AI Worms: How Copilot for Word Propagates Hidden Attacks Across Documents
Maliciously crafted documents can turn Microsoft Copilot into a self-propagating AI worm that silently alters and infects internal document workflows.
Adversarial Machine Learning
The study of attacks that manipulate machine learning models by crafting specially designed inputs, and the defenses developed to counter them.
Reading List
The Illusion of AI Intelligence: Why Bots Can't Be Prompted Into Being Smart
158
AI agents are easily subverted by hidden instructions because they lack the intelligence to distinguish between data and commands.
The Hidden Security Risks of Voice AI
140
Voice AI systems can be covertly controlled by audio signals that are undetectable or unrecognizable to human listeners.