SoWaF: Shuffling of Weights and Feature Maps: A Novel Hardware Intrinsic Attack (HIA) on Convolutional Neural Network (CNN)
This work addresses a security vulnerability for embedded systems using CNNs, presenting a novel attack method that is incremental in showing how existing secure practices can be compromised.
The paper tackles the security of CNN inference on resource-constrained embedded systems by demonstrating a hardware intrinsic attack (HIA) that can bypass secure designs where attackers lack knowledge of initial and final layers, resulting in misclassification with negligible additional latency (<0.61%) and low resource overhead (<2.36% increase in DSP, LUT, FF).
Security of inference phase deployment of Convolutional neural network (CNN) into resource constrained embedded systems (e.g. low end FPGAs) is a growing research area. Using secure practices, third party FPGA designers can be provided with no knowledge of initial and final classification layers. In this work, we demonstrate that hardware intrinsic attack (HIA) in such a "secure" design is still possible. Proposed HIA is inserted inside mathematical operations of individual layers of CNN, which propagates erroneous operations in all the subsequent CNN layers that lead to misclassification. The attack is non-periodic and completely random, hence it becomes difficult to detect. Five different attack scenarios with respect to each CNN layer are designed and evaluated based on the overhead resources and the rate of triggering in comparison to the original implementation. Our results for two CNN architectures show that in all the attack scenarios, additional latency is negligible (<0.61%), increment in DSP, LUT, FF is also less than 2.36%. Three attack scenarios do not require any additional BRAM resources, while in two scenarios BRAM increases, which compensates with the corresponding decrease in FF and LUTs. To the authors' best knowledge this work is the first to address the hardware intrinsic CNN attack with the attacker does not have knowledge of the full CNN.