Tootfinder

Stealing AI Model Weights Through Covert Communication Channels
Valentin Barbaza, Alan Rodrigo Diaz-Rizo, Hassan Aboushady, Spyridon Raptis, Haralampos-G. Stratigopoulos
https://arxiv.org/abs/2510.00151

Stealing AI Model Weights Through Covert Communication Channels
AI models are often regarded as valuable intellectual property due to the high cost of their development, the competitive advantage they provide, and the proprietary techniques involved in their creation. As a result, AI model stealing attacks pose a serious concern for AI model providers. In this work, we present a novel attack targeting wireless devices equipped with AI hardware accelerators. The attack unfolds in two phases. In the first phase, the victim's device is compromised with a hardw…