Prediction and Detection of FDIA and DDoS Attacks in 5G Enabled IoT

Abstract

Security in the fifth generation (5G) networks has become one of the prime concerns in the telecommunication industry. 5G security challenges come from the fact that 5G networks involve different stakeholders using different security requirements and measures. Deficiencies in security management between these stakeholders can lead to security attacks. Therefore, security solutions should be conceived for the safe deployment of different 5G verticals (e.g., industry 4.0, Internet of Things (IoT), etc.). The interdependencies among 5G and fully connected systems, such as IoT, entail some standard security requirements, namely integrity, availability, and confidentiality. In this article, we propose a hierarchical architecture for securing 5G enabled IoT networks, and a security model for the prediction and detection of False Data Injection Attacks (FDIA) and Distributed Denial of Service attacks (DDoS). The proposed security model is based on a Markov stochastic process, which is used to observe the behavior of each network device, and employ a range-based behavior sifting policy. Simulation results demonstrate the effectiveness of the proposed architecture and model in detecting and predicting FDIA and DDoS attacks in the context of 5G enabled IoT.

An Overview of Blockchain and 5G Networks

“…security improvements 5G networks face several security challenges, from data privacy to authentication vulnerability such as frequent authentication applied to ultra-dense networks [22]. These challenges expose 5G networks to attacks and increase their impact.…”

Data-Quality Based Scheduling for Federated Edge Learning

“…Data Quality and Data Poisoning 1) Data Poisoning in FEEL In FEEL, UE data may include personal information (e.g., home address, credit card number, etc.). The disclosure of this data is not only harmful to the UE, but the intentional/unintentional alteration of the data can also cause security problems [21]. One of the main types of attacks that can affect model severally is poisoning attack.…”

Towards a Secure and Reliable Federated Learning using Blockchain

“…Although machine learning has significantly improved the performance of many applications, most machine learning models must be built in central servers, which may violate privacy, especially for users with sensitive data [1,2,3]. This is because to participate in learning a model, users/devices trade their privacy by sending their sensitive data to the central server [4]. To overcome this problem, Google proposed Federated Learning (FL) to locally train models on edge devices while keeping their data private [5,6].…”