Self-Supervised Adversarial Example Detection by Disentangled Representation

Deep learning models are known to be vulnerable to adversarial examples that are elaborately designed for malicious purposes and are imperceptible to the human perceptual system. Autoencoder, when trained solely over benign examples, has been widely used for (self-supervised) adversarial detection based on the assumption that adversarial examples yield larger reconstruction errors. However, because lacking adversarial examples in its training and the too strong generalization ability of autoencoder, this assumption does not always hold true in practice. To alleviate this problem, we explore how to detect adversarial examples with disentangled label/semantic features under the autoencoder structure. Specifically, we propose Disentangled Representationbased Reconstruction (DRR). In DRR, we train an autoencoder over both correctly paired label/semantic features and incorrectly paired label/semantic features to reconstruct benign and counterexamples. This mimics the behavior of adversarial examples and can reduce the unnecessary generalization ability of autoencoder. We compare our method with the state-of-the-art selfsupervised detection methods under different adversarial attacks and different victim models, and it exhibits better performance in various metrics (area under the ROC curve, true positive rate, and true negative rate) for most attack settings. Though DRR is initially designed for visual tasks only, we demonstrate that it can be easily extended for natural language tasks as well. Notably, different from other autoencoder-based detectors, our method can provide resistance to the adaptive adversary.