Deep neural networks (DNNs) have been found vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. There are various approaches to detect backdoor attacks, however they all make certain assumptions about the target attack to be detected and require equal and huge numbers of clean and backdoor samples for training, which renders these detection methods quite limiting in real-world circumstances. This study proposes a novel one-class classification framework called One-class Graph Embedding Classification (OCGEC) that uses GNNs for model-level backdoor detection with only a little amount of clean data. First, we train thousands of tiny models as raw datasets from a small number of clean datasets. Following that, we design a ingenious model-to-graph method for converting the model's structural details and weight features into graph data. We then pre-train a generative self-supervised graph autoencoder (GAE) to better learn the features of benign models in order to detect backdoor models without knowing the attack strategy. After that, we dynamically combine the GAE and one-class classifier optimization goals to form classification boundaries that distinguish backdoor models from benign models. Our OCGEC combines the powerful representation capabilities of graph neural networks with the utility of one-class classification techniques in the field of anomaly detection. In comparison to other baselines, it achieves AUC scores of more than 98% on a number of tasks, which far exceeds existing methods for detection even when they rely on a huge number of positive and negative samples. Our pioneering application of graphic scenarios for generic backdoor detection can provide new insights that can be used to improve other backdoor defense tasks. Code is available at https://github.com/jhy549/OCGEC.
Deep learning has shown impressive performance on challenging perceptual tasks and has been widely used in software to provide intelligent services. However, researchers found deep neural networks vulnerable to adversarial examples. Since then, many methods are proposed to defend against adversaries in inputs, but they are either attack-dependent or shown to be ineffective with new attacks. And most of existing techniques have complicated structures or mechanisms that cause prohibitively high overhead or latency, impractical to apply on real software. We propose DAFAR, a feedback framework that allows deep learning models to detect/purify adversarial examples in high effectiveness and universality, with low area and time overhead. DAFAR has a simple structure, containing a victim model, a plug-in feedback network, and a detector. The key idea is to import the high-level features from the victim model's feature extraction layers into the feedback network to reconstruct the input. This data stream forms a feedback autoencoder. For strong attacks, it transforms the imperceptible attack on the victim model into the obvious reconstruction-error attack on the feedback autoencoder directly, which is much easier to detect; for weak attacks, the reformation process destroys the structure of adversarial examples. Experiments are conducted on MNIST and CIFAR-10 data-sets, showing that DAFAR is effective against popular and arguably most advanced attacks without losing performance on legitimate samples, with high effectiveness and universality across attack methods and parameters.
Deep learning has shown impressive performance on challenging perceptual tasks. However, researchers found deep neural networks vulnerable to adversarial examples. Since then, many methods are proposed to defend against or detect adversarial examples, but they are either attack-dependent or shown to be ineffective with new attacks. We propose DAFAR, a feedback framework that allows deep learning models to detect adversarial examples in high accuracy and universality. DAFAR has a relatively simple structure, which contains a target network, a plug-in feedback network and an autoencoder-based detector. The key idea is to capture the high-level features extracted by the target network, and then reconstruct the input using the feedback network. These two parts constitute a feedback autoencoder. It transforms the imperceptible-perturbation attack on the target network directly into obvious reconstruction-error attack on the feedback autoencoder. Finally the detector gives an anomaly score and determines whether the input is adversarial according to the reconstruction errors. Experiments are conducted on MNIST and CIFAR-10 data-sets. Experimental results show that DAFAR is effective against popular and arguably most advanced attacks without losing performance on legitimate samples, with high accuracy and universality across attack methods and parameters.