# Revealing CNN Architectures via Side-Channel Analysis in Dataflow-based Inference Accelerators

arXiv: https://arxiv.org/abs/2311.00579 · HTML: https://mlsanity.com/paper/2311.00579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures](https://mlsanity.com/paper/1808.04761/) (2018)
- [Open DNN Box by Power Side-Channel Attack](https://mlsanity.com/paper/1907.10406/) (2019)
- [Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints](https://mlsanity.com/paper/1903.03916/) (2019)
- [DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs](https://mlsanity.com/paper/2007.15248/) (2020)
- [Security of Electrical, Optical and Wireless On-Chip Interconnects: A Survey](https://mlsanity.com/paper/2301.09738/) (2023)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are widely used in various domains, including image recognition, medical diagnosis and autonomous driving. Recent advances in dataflow-based CNN accelerators have enabled CNN inference in resource-constrained edge devices. These dataflow accelerators utilize inherent data reuse of convolution layers to process CNN models efficiently. Concealing the architecture of CNN models is critical for privacy and security. This article evaluates memory-based side-channel information to recover CNN architectures from dataflow-based CNN inference accelerators. The proposed attack exploits spatial and temporal data reuse of the dataflow mapping on CNN accelerators and architectural hints to recover the structure of CNN models. Experimental results demonstrate that our proposed side-channel attack can recover the structures of popular CNN models, namely, Lenet, Alexnet, VGGnet16, and YOLOv2.