Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks
This work addresses the need for faster adversarial attacks to enhance deep learning security, but it is incremental as it focuses on hardware optimization rather than new algorithmic breakthroughs.
The paper tackles the problem of slow adversarial attack generation due to algorithmic complexity by proposing the first hardware accelerator using memristor crossbar arrays, resulting in significant throughput improvements for visual adversarial perturbation systems.
Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs. A class of adversarial attack network algorithms has been proposed to generate robust physical perturbations under different circumstances. These algorithms are the first efforts to move forward secure deep learning by providing an avenue to train future defense networks, however, the intrinsic complexity of them prevents their broader usage. In this paper, we propose the first hardware accelerator for adversarial attacks based on memristor crossbar arrays. Our design significantly improves the throughput of a visual adversarial perturbation system, which can further improve the robustness and security of future deep learning systems. Based on the algorithm uniqueness, we propose four implementations for the adversarial attack accelerator ($A^3$) to improve the throughput, energy efficiency, and computational efficiency.