Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things
This addresses the challenge of securing Deep Learning as a service in IoT against adversarial attacks, offering a more efficient and generalizable defense compared to existing methods.
The paper tackles the problem of defending Deep Neural Networks against adversarial attacks in IoT by proposing a progressive defense strategy that efficiently filters adversarial pixel mutations without prior knowledge of attack types, achieving state-of-the-art performance while reducing model training costs by 50% on average.
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.