RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks

TL;DR

This paper introduces RESQ, a three-stage framework that enhances the robustness of quantized deep neural networks against both faults and attacks, balancing security and efficiency.

Contribution

It presents a novel unified framework with fine-tuning and post-training adjustments to improve fault and attack resilience in quantized DNNs.

Findings

Up to 10.35% improvement in attack resilience

Up to 12.47% improvement in fault resilience

Maintains competitive accuracy in quantized networks

Abstract

This work proposes a unified three-stage framework that produces a quantized DNN with balanced fault and attack robustness. The first stage improves attack resilience via fine-tuning that desensitizes feature representations to small input perturbations. The second stage reinforces fault resilience through fault-aware fine-tuning under simulated bit-flip faults. Finally, a lightweight post-training adjustment integrates quantization to enhance efficiency and further mitigate fault sensitivity without degrading attack resilience. Experiments on ResNet18, VGG16, EfficientNet, and Swin-Tiny in CIFAR-10, CIFAR-100, and GTSRB show consistent gains of up to 10.35% in attack resilience and 12.47% in fault resilience, while maintaining competitive accuracy in quantized networks. The results also highlight an asymmetric interaction in which improvements in fault resilience generally increase resilience to adversarial attacks, whereas enhanced adversarial resilience does not necessarily lead to higher fault resilience.