Advancing NDN Security for IoT: Harnessing Machine Learning to Detect Attacks

As the Internet of Things (IoT) increasingly integrates into our daily lives, ensuring its secure connectivity emerges as a fundamental necessity. In response to this need, this paper investigates mechanisms that can be used to enhance the security of IoT by leveraging Named Data Networking (NDN). NDN has been a promising technology for IoT as it can store data within the network and has built-in security features. However, it is vulnerable to a wide range of cyber attacks, including Side-channel Timing Attacks (SCTA), Cache Pollution Attacks (CPA), and Interest Flooding Attacks (IFA). To address these challenges, our paper focuses on developing a comprehensive attack dataset, comprising the aforementioned attacks and a unified detection and classification strategy has been achieved through machine learning. Our findings demonstrate a high degree of efficacy, with our solution showcasing a 98% attack detection accuracy rate.