一句话：提出图引导测试 GGT，通过图特征生成高多样性剪枝模型，高效检测 DNN 对抗样本。
深度神经网络易受对抗样本攻击，检测对抗样本对模型应用至关重要。已有软件测试方法中的模型变异测试（MMT）能检测多种对抗样本，但其变异模型数量庞大（常超过 100 个）且缺乏多样性，容易被高置信度对抗样本规避，效率和效果均受限。本文提出图引导测试（Graph-Guided Testing, GGT），在图特征指导下生成剪枝模型，每个模型仅约 MMT 变异模型 5% 的参数，且图引导模型具有更高多样性。在 CIFAR10 上的初步实验表明，GGT 在检测效果和效率上均显著优于 MMT。
Deep Neural Networks (DNN) are known to be vulnerable to adversarial samples, the detection of which is crucial for the wide application of these DNN models. Recently, a number of deep testing methods in software engineering were proposed to find the vulnerability of DNN systems, and one of them, i.e., Model Mutation Testing (MMT), was used to successfully detect various adversarial samples generated by different kinds of adversarial attacks. However, the mutated models in MMT are always huge in number (e.g., over 100 models) and lack diversity (e.g., can be easily circumvented by high-confidence adversarial samples), which makes it less efficient in real applications and less effective in detecting high-confidence adversarial samples. In this study, we propose Graph-Guided Testing (GGT) for adversarial sample detection to overcome these aforementioned challenges. GGT generates pruned models with the guide of graph characteristics, each of them has only about 5% parameters of the mutated model in MMT, and graph guided models have higher diversity. The initial experiments on CIFAR10 validate that GGT performs much better than MMT with respect to both effectiveness and efficiency.
DOI 原文 ·
@inproceedings{paperbot6609,
title = {Detecting Adversarial Samples with Graph-Guided Testing},
author = {Zuohui Chen and Renxuan Wang and Jingyang Xiang and Yue Yu and Xin Xia and Shouling Ji and Qi Xuan and Xiaoniu Yang},
booktitle = {ASE},
year = {2021},
doi = {10.1109/ase51524.2021.9678732}
}