High-speed interconnects, such as NVLink, are integral to modern multi-GPU systems, acting as a vital link between CPUs and GPUs. This study highlights the vulnerability of multi-GPU systems to covert and side channel attacks due to congestion on interconnects. An adversary can infer private information about a victim's activities by monitoring NVLink congestion without needing special permissions. Leveraging this insight, we develop a covert channel attack across two GPUs with a bandwidth of 45.5 kbps and a low error rate, and introduce a side channel attack enabling attackers to fingerprint applications through the shared NVLink interconnect.
@article{arxiv.2404.03877,
title = {Beyond the Bridge: Contention-Based Covert and Side Channel Attacks on Multi-GPU Interconnect},
author = {Yicheng Zhang and Ravan Nazaraliyev and Sankha Baran Dutta and Nael Abu-Ghazaleh and Andres Marquez and Kevin Barker},
journal= {arXiv preprint arXiv:2404.03877},
year = {2024}
}