Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things

Abstract

Nowadays, Deep Learning as a service can be deployed in Internet of Things (IoT) to provide smart services and sensor data processing. However, recent research has revealed that some Deep Neural Networks (DNN) can be easily misled by adding relatively small but adversarial perturbations to the input (e.g., pixel mutation in input images). One challenge in defending DNN against these attacks is to efficiently identifying and filtering out the adversarial pixels. The state-of-the-art defense strategies with good robustness often require additional model training for specific attacks. To reduce the computational cost without loss of generality, we present a defense strategy called a progressive defense against adversarial attacks (PDAAA) for efficiently and effectively filtering out the adversarial pixel mutations, which could mislead the neural network towards erroneous outputs, without a-priori knowledge about the attack type. We evaluated our progressive defense strategy against various attack methods on two well-known datasets. The result shows it outperforms the state-of-the-art while reducing the cost of model training by 50% on average.

References in corpus (5)

• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples
• A Direct Approach to Robust Deep Learning Using Adversarial Networks
• Adversary Detection in Neural Networks via Persistent Homology