Ensuring IoT Privacy using Padding Strategies against Machine Learning Approaches

Abstract

– The widespread usage of Internet of Things (IoT) devices is increasing by the recent advances in embedded systems, cloud computing, artificial intelligence, and wireless communications. Besides, a huge amount of data is transmitted between IoT devices over insecure networks. The transferred data can be sensitive and confidential. On the other hand, these transmitted data may not appear to be sensitive or confidential data. However, machine learning techniques are used on these non-confidential data (such as packet length) to obtain data such as the type of the IoT device. An observer can monitor traffic to infer sensitive data by using machine learning techniques to analyze the generated encrypted traffic. For this purpose, padding can be added to the packets to ensure traffic privacy. This paper presents privacy problems that are caused by the traffic generated during the communication of IoT devices. Also, security and privacy measures that should be taken against the related privacy problems are explained. For this purpose, the current studies are examined by considering the attacker and the defender models.