4 papers
Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
Spyridon Raptis, Haralampos-G. Stratigopoulos
Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on neuromorphic hardware and motiva…
Stealing AI Model Weights Through Covert Communication Channels
Valentin Barbaza, Alan Rodrigo Diaz-Rizo, Hassan Aboushady +2
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 inv…
Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain
Spyridon Raptis, Haralampos-G. Stratigopoulos
As Spiking Neural Networks (SNNs) gain traction across various applications, understanding their security vulnerabilities becomes increasingly important. In this work, we focus on…
Input-Triggered Hardware Trojan Attack on Spiking Neural Networks
Spyridon Raptis, Paul Kling, Ioannis Kaskampas +2
Neuromorphic computing based on spiking neural networks (SNNs) is emerging as a promising alternative to traditional artificial neural networks (ANNs), offering unique advantages i…