Special Issue on Adversarial AI to IoT Security and Privacy Protection: Attacks and Defenses

The prosperity of social IoT data brings revolutionary changes to our daily lives and greatly increases the existing data volume. But IoT data are vulnerable due to security and privacy issues. Over the past few years, malicious adversaries exploited various vulnerabilities of AI algorithms and thus compromised the security of AI systems. For example, obfuscating malware code within benign programs or applications to fool the AI-based intrusion detection systems. Thus, applying adversarial AI is supposed to be one of the most useful methods to protect IoT data, including big data mining and analysis, information diffusion, sentiment analysis and opinion mining, social event detection, trend prediction and influence maximization. This special issue brings together leading researchers and developers presenting their latest research and 10 high-quality papers are selected. A summary of these accepted papers is outlined below. In the paper entitled 'AWFC: Preventing Label Flipping Attacks towards Federated Learning for Intelligent IoT' by Zhuo Lv et al., the authors are motivated to prevent label flipping poisoning attacks by observing the changes in model parameters that were trained by different single labels. They propose a novel detection method, called AWFC, that label flipping attacks are detected by identifying the differences of classes in the data. The weight assignments in a fully connected layer of the neural network model are used and the statistical algorithm is applied to find the malicious clients. The experiments are conducted on benchmark data, such as Fashion-MNIST and Intrusion Detection Evaluation Dataset (CIC-IDS2017), where results demonstrate that the method's detection accuracy is better.