Abstract
In this work, we consider secure communications in wireless multi-user (MU) multiple-input single-output (MISO) systems with channel coding in the presence of a multi-antenna eavesdropper (Eve), who is a legit user trying to eavesdrop other users. In this setting, we exploit machine learning (ML) tools to design soft and hard decoding schemes by using precoded pilot symbols as training data. The proposed ML frameworks allow an Eve to determine the transmitted message with high accuracy. We thereby show that MU-MISO systems are vulnerable to such eavesdropping attacks even when relatively secure transmission techniques are employed, such as symbol-level precoding (SLP). To counteract this attack, we propose two novel SLP-based schemes that increase the bit-error rate at Eve by impeding the learning process. We design these two security-enhanced schemes to meet different requirements regarding runtime, security, and power consumption. Simulation results validate both the ML-based eavesdropping attacks as well as the countermeasures, and show that the gain in security is achieved without affecting the decoding performance at the intended users.
Highlights
While fifth generation (5G) cellular networks are currently being provisioned worldwide, its successor generation, named 6G wireless system, is being proposed to overcome several limitations in 5G [1]–[3]
The essence of physical-layer security (PLS) is to exploit the characteristics of the wireless channel, i.e., fading, noise, interference, and diversity, to attain an acceptable decoding performance at intended users while obstructing the correct decoding at Eve
To make this section more comprehensive, we split it into three parts: 1) Parameters, metrics, and benchmarks where we defined the simulations’ setting, 2) selection of machine learning (ML) algorithms for Eve attack in which we experiment with several algorithms and select the most performing, and 3) comparisons and insights to assess the performance of our proposed schemes in terms of security, power consumption, and runtime
Summary
While fifth generation (5G) cellular networks are currently being provisioned worldwide, its successor generation, named 6G wireless system, is being proposed to overcome several limitations in 5G [1]–[3]. The primary contributions of the paper are listed below: 1) We introduce eavesdropping attacks in MU-MISO systems with FEC by proposing novel ML-based soft and hard decoding schemes, where a multi-antenna Eve can use ML and the knowledge of pilot symbols as well as the added redundancy related to channel coding to decode the transmitted data with high accuracy. 3) To counteract these eavesdropping attacks, we propose two security-enhanced SLP-based schemes that aim to increase the BER at Eve by impeding the learning process This is performed by either embedding randomness in Eve’s received signal or minimizing Eve’s received power. Upper and lower boldface symbols are used to denote matrices and column vectors, respectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
