From the 1 of 7 linked papers with an AI index.
7 papers
Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
Spyridon Raptis, Haralampos-G. Stratigopoulos
The paper demonstrates that spiking neural networks, which are energy‑efficient on neuromorphic hardware, can be targeted by adversarial "sponge" attacks that increase spike activi…
A Heterogeneous Neural Network Accelerator for End-to-End Multitask RF Signal Recognition
Zhifan Song, Haralampos-G. Stratigopoulos, Hassan Aboushady
This paper presents a heterogeneous neural network accelerator for multi-task RF signal recognition, supporting automatic modulation recognition (AMR), hardware-Trojan covert chann…
Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring
Zhifan Song, Haralampos-G. Stratigopoulos, Hassan Aboushady
We present E-SpecFormer (Edge Spectrum monitoring Transformer) for end-to-end automatic modulation and covert channel (CC) recognition. We introduce LiTAN (Linear Tanh Attention Ne…
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…