NNTesting: Neural Network Fault Attacks Detection Using Gradient-Based Test Vector Generation

Antian Wang, Bingyin Zhao, Weihang Tan, Yingjie Lao

Abstract: Recent studies have shown Neural Networks (NNs) are highly vulnerable to fault attacks. This work proposes a novel defensive framework, NNTesting, for detecting the fault attack and recovering the model. We first leverage gradient-based optimization to generate a set of high-quality Test Vectors (TVs) that effectively differentiate faulty profile models and further optimize the TV set by reducing the TVs through compression. The selected final TV set is then used to recover the model. The effectiveness of the proposed method is comprehensively evaluated on a wide range of models across various benchmark datasets. For instance, we successfully generate more than thousands of TV candidates using a gradient-based generation method. After compression, we achieve up to 94.76% detection success rate with only 140 TVs on the CIFAR-10 dataset.