defense arXiv Mar 16, 2026 · 21d ago
Ali Soltan Mohammadi, Samira Nazari, Ali Azarpeyvand et al. · University of Zanjan · Brandenburg Technical University +2 more
Defense framework combining adversarial training and fault-aware fine-tuning to produce quantized DNNs resilient to both adversarial attacks and hardware bit-flip faults
Input Manipulation Attack vision
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.
cnn transformer University of Zanjan · Brandenburg Technical University · Tallinn University of Technology +1 more
ML Security Papers