Can one hear the shape of a neural network?: Snooping the GPU via Magnetic Side Channel
Henrique Teles Maia, Chang Xiao, Dingzeyu Li, Eitan Grinspun, Changxi, Zheng

TL;DR
This paper demonstrates that electromagnetic side channels can reveal detailed information about neural network architectures deployed on GPUs, posing security risks and highlighting the need for protective measures.
Contribution
It introduces a novel magnetic side channel attack that can reconstruct neural network topology and hyperparameters from electromagnetic signals emitted during GPU computation.
Findings
Magnetic flux signals correlate with neural network layer evaluations
Layer topology and hyperparameters can be inferred with high accuracy
Potential for adversarial attacks exploiting this side channel
Abstract
Neural network applications have become popular in both enterprise and personal settings. Network solutions are tuned meticulously for each task, and designs that can robustly resolve queries end up in high demand. As the commercial value of accurate and performant machine learning models increases, so too does the demand to protect neural architectures as confidential investments. We explore the vulnerability of neural networks deployed as black boxes across accelerated hardware through electromagnetic side channels. We examine the magnetic flux emanating from a graphics processing unit's power cable, as acquired by a cheap $3 induction sensor, and find that this signal betrays the detailed topology and hyperparameters of a black-box neural network model. The attack acquires the magnetic signal for one query with unknown input values, but known input dimensions. The network…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Memory and Neural Computing · Adversarial Robustness in Machine Learning · Neural Networks and Applications
