Traffic classification is widely used in various network functions such as software-defined networking and network intrusion detection systems. Many traffic classification methods have been proposed for classifying encrypted traffic by utilizing a deep learning model without inspecting the packet payload. However, they have an important challenge in that the mechanism of deep learning is inexplicable. A malfunction of the deep learning model may occur if the training dataset includes malicious or erroneous data. Explainable artificial intelligence (XAI) can give some insight for improving the deep learning model by explaining the cause of the malfunction. In this paper, we propose a method for explaining the working mechanism of deep-learning-based traffic classification as a method of XAI based on a genetic algorithm. We describe the mechanism of the deep-learning-based traffic classifier by quantifying the importance of each feature. In addition, we leverage the genetic algorithm to generate a feature selection mask that selects important features in the entire feature set. To demonstrate the proposed explanation method, we implemented a deep-learning-based traffic classifier with an accuracy of approximately 97.24%. In addition, we present the importance of each feature derived from the proposed explanation method by defining the dominance rate.

Recently, cybercrimes that exploit the anonymity of blockchain are increasing. They steal blockchain users’ assets, threaten the network’s reliability, and destabilize the blockchain network. Therefore, it is necessary to detect blockchain cybercriminal accounts to protect users’ assets and sustain the blockchain ecosystem. Many studies have been conducted to detect cybercriminal accounts in the blockchain network. They represented blockchain transaction records as homogeneous transaction graphs that have a multi-edge. They also adopted graph learning algorithms to analyze transaction graphs. However, most graph learning algorithms are not efficient in multi-edge graphs, and homogeneous graphs ignore the heterogeneity of the blockchain network. In this paper, we propose a novel heterogeneous graph structure called an account-transaction graph, ATGraph. ATGraph represents a multi-edge as single edges by considering transactions as nodes. It allows graph learning more efficiently by eliminating multi-edges. Moreover, we compare the performance of ATGraph with homogeneous transaction graphs in various graph learning algorithms. The experimental results demonstrate that the detection performance using ATGraph as input outperforms that using homogeneous graphs as the input by up to 0.2 AUROC.

Space-air-ground integrated networks (SAGIN) are receiving a lot of attention as a candidate for an extension to non-terrestrial networks beyond the limit of terrestrial networks. SAGIN can be a means to satisfy various quality-of-service (QoS) by providing several communication links in different characteristics. To fully utilize the advantage of SAGIN, a protocol for informing user equipment (UE) of an appropriate base station layer of SAGIN is needed according to QoS requirements. In addition, the development of the protocol should consider the characteristics of the UE. In particular, when the UE is a machine-type communication device (MTCD) constituting a massive internet of things network, random access congestion issue should be considered. To solve the problems, we propose a random access protocol. We propose an indicator named virtual deadline indicator (VDI) to inform MTCD which layer to try for random access. MTCD attempts random access to one layer of SAGIN by comparing the remaining deadlines of traffic and the point of the VDI. To minimize the deadline expiration rate, we propose an algorithm to shift the VDI position. The base station estimates the number of the MTCDs and remaining deadline distribution by using the number of the idle preambles to find the VDI location. Finally, we compare the performance of the protocol through simulation with three benchmark schemes. We confirm that the proposed protocol reduces the deadline expiration rate without compromising the age of information and energy efficiency.

Cell-free massive multiple-input multiple-output (CF-mMIMO) can provide uniformly great service to user equipment (UE) by utilizing a large number of distributed access points (APs) connected to a single central processing unit (CPU). For addressing scalability and feasibility issues inherent in single-CPU CF-mMIMO systems, multiple-CPU CF-mMIMO (MC-CF-mMIMO) has been considered. However, the MC-CF-mMIMO system inevitably encounters performance degradation at the boundary area of the CPUs, referred to as the CPU edge. Cooperation among CPUs can improve the performance in the CPU edge region; however, scalability problems resurface owing to inter-CPU information sharing during the cooperation process. In this study, we propose a scalable CPU cooperation scheme that focuses on power control to address the performance degradation issue in the CPU edge region. Initially, we propose a policy estimation scheme for other CPUs to reduce the overhead of information sharing. Based on these estimated policies, each CPU can independently derive power control policies for the max-min optimization problem without simultaneous information sharing. Simulation results show that the proposed power control scheme achieves a performance improvement of up to 4.3234 dB in terms of CPU edge region performance and minimum spectral efficiency compared to baseline schemes based on the degree of CPU cooperation.

This study addresses the challenge of high-power collision rates in grant-free nonorthogonal random access (GF-NORA) for ultramassive machine-type communication (umMTC) in ultradense networks (UDNs). We analyze the impact of power collision and intercell interference, defining the key factors affecting successive interference cancelation (SIC) decoding failure. To tackle power collision problem, we propose a multiagent reinforcement learning (MARL) framework, QMIX algorithm, with joint optimization of access control and power-level design. We evaluate the performance of the proposed scheme with extensive random access simulations in an umMTC environment. Our approach outperforms state-of-the-art schemes, achieving at most 10% increase in successful SIC decoding rate with lower access delay.