We introduce CyBERT, a cybersecurity feature claims classifier based on bidirectional encoder representations from transformers and a key component in our semi-automated cybersecurity vetting for industrial control systems (ICS). To train CyBERT, we created a corpus of labeled sequences from ICS device documentation collected across a wide range of vendors and devices. This corpus provides the foundation for fine-tuning BERT’s language model, including a prediction-guided relabeling process. We propose an approach to obtain optimal hyperparameters, including the learning rate, the number of dense layers, and their configuration, to increase the accuracy of our classifier. Fine-tuning all hyperparameters of the resulting model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original architecture to 94.4% obtained with CyBERT. Furthermore, we evaluated CyBERT for the impact of randomness in the initialization, training, and data-sampling phases. CyBERT demonstrated a standard deviation of ±0.6% during validation across 100 random seed values. Finally, we also compared the performance of CyBERT to other well-established language models including GPT2, ULMFiT, and ELMo, as well as neural network models such as CNN, LSTM, and BiLSTM. The results showed that CyBERT outperforms these models on the validation accuracy and the F1 score, validating CyBERT’s robustness and accuracy as a cybersecurity feature claims classifier.

With the rapid rollout and growing adoption of 3GPP 5thGeneration (5G) cellular services, including in critical infrastructure sectors, it is important to review security mechanisms, risks, and potential vulnerabilities within this vital technology. Numerous security capabilities need to work together to ensure and maintain a sufficiently secure 5G environment that places user privacy and security at the forefront. Confidentiality, integrity, and availability are all pillars of a privacy and security framework that define major aspects of 5G operations. They are incorporated and considered in the design of the 5G standard by the 3rd Generation Partnership Project (3GPP) with the goal of providing a highly reliable network operation for all. Through a comprehensive review, we aim to analyze the ever-evolving landscape of 5G, including any potential attack vectors and proposed measures to mitigate or prevent these threats. This paper presents a comprehensive survey of the state-of-the-art research that has been conducted in recent years regarding 5G systems, focusing on the main components in a systematic approach: the Core Network (CN), Radio Access Network (RAN), and User Equipment (UE). Additionally, we investigate the utilization of 5G in time-dependent, ultra-confidential, and private communications built around a Zero Trust approach. In today’s world, where everything is more connected than ever, Zero Trust policies and architectures can be highly valuable in operations containing sensitive data. Realizing a Zero Trust Architecture entails continuous verification of all devices, users, and requests, regardless of their location within the network, and grants permission only to authorized entities. Finally, developments and proposed methods of new 5G and future 6G security approaches, such as Blockchain technology, post-quantum cryptography (PQC), and Artificial Intelligence (AI) schemes, are also discussed to understand better the full landscape of current and future research within this telecommunications domain.

Cognitive radio (CR) has been introduced into the Internet of Things (IoT) domain as a potential solution to the critical spectrum resource shortage caused by a dramatic increase of IoT solutions within a limited operational spectrum. One technique of use within traditional CR processing for sensing communication activity across a spectrum of interest is automatic modulation classification (AMC). However, utilizing AMC within resource-limited cognitive radio-enabled IoT (CR-IoT) devices poses a significant challenge. In this article, we present a high-efficiency automatic modulation classifier architecture whose core is built upon the implementation of stacking quasirecurrent neural network (S-QRNN) layers acting as a feature extraction stage. This architecture utilizes the low-latency feature extraction capability of convolutional layers, and a minimalist recurrent pooling function that mimics recurrent-layer operations to aggregate the extracted features over time steps for higher classification accuracy. Additionally, implementing dense layers between two consecutive QRNN layers helps keep the network growth rate low. Therefore, the proposed S-QRNN classifier overall exhibits higher efficiency, fitting well within the limitations of CR-IoT devices. In order to demonstrate higher performance efficiency of our classifier, we conduct a comprehensive evaluation of our approach against the state-of-the-art AMC classifiers. Our analysis metrics of the classifier performance focuses on trainability, classification accuracy, execution latency, and resulting overall efficiency. Our results demonstrate that our proposed S-QRNN classifier exhibits higher trainability and, on average, a 75.83% higher efficiency, while it has, on average, a 26.54% lower execution latency. We then expand upon S-QRNN’s foundation by introducing gated recurrent units into our classifier to initially extract temporal features of the received constellations. The resulting GS-QRNN classifier demonstrates an efficiency increase by an average of 191% compared to the gated-enhanced recurrent-neural-network-based AMC classifier, with our GS-QRNN classifier average execution latency being 59.31% lower.

Automatic Modulation Classification (AMC) is an approach to identify an observed signal's most likely modulation scheme without any a priori knowledge of the intercepted signal. In this research, the authors present a new direction for both stages of feature-based (FB) approach. In the feature extraction stage, the authors design a new architecture that 1) removes the bias issue for the estimator of fourth-order cumulants, and 2) extracts polar-transformed information of the received IQ symbols, and finally 3) forms a unique dataset to be used in the labeling stage. Furthermore, the authors contribute to increasing the classification accuracy in low signal-to-noise ratio (SNR) conditions by employing the deep belief network (DBN) platform in addition to the spiking neural network (SNN) platform to overcome execution latency concerns associated with deep learning architectures. For this research, the authors first study each individual FB AMC classifier to derive their respective upper and lower performance bounds and then propose an adaptive framework that is built and developed with these findings. This framework aims to efficiently classify the modulation scheme by intelligently switching between these different FB classifiers to achieve an optimal balance between accuracy and execution latency for any observed channel conditions derived from the main receiver's equalizer. Subsequently, a performance analysis is conducted using the standard RadioML dataset to achieve a realistic evaluation. Numerical results indicate a notably higher classification accuracy, by 16.02% on average, when DBN is employed, whereas SNN requires significantly lower execution latency to label the modulation scheme when compared against two other modified FB classifiers that are built upon convolutional and recurrent neural networks, shown to be reduced by 34.31%.

Automatic modulation identification (AMI) is a technique to detect the modulation type and order of a received signal, which has the potential to enhance cognitive radio capabilities for future generations of communication devices. However, AMI classifiers traditionally have exhibited low efficiency in low signal-to-noise ratio (SNR) environments. Hence, to address this problem we present our novel Gated Graph Convolutional Neural Network (GGCNN) classifier for feature-based AMI. This architecture includes a robust feature extraction stage to extract deep correlative patterns about the received symbols. Not only does this feature extraction stage use the temporal characteristics of the received symbols, but it also takes advantage of embedded signaling features from the received signal. In the proposed classifier, the received constellations are treated as a graph, allowing it to outperform state-of-the-art classifiers due to its strong performance in graph classification. This is observed clearly in the visualization of the extracted features, even for high-order modulation schemes. In this paper, we present our systematic research conducted for maximizing the efficiency obtainable by our classifier. Extensive simulation results demonstrate a significant accuracy improvement of 18.44 percentage points, and an efficiency increase by 60.78% for our GGCNN-AMI classifier compared to state-of-the-art classifiers in low-SNR environments.

Fifth Generation (5G) cellular networks have been adopted worldwide since the rollout began around 2019. It brought with it many innovations and new services, such as Enhanced Mobile Broadband (eMBB), Ultra Reliable and Low-Latency Communications (URLLC), and Massive Internet of Things (mIoT). Furthermore, 5G introduced a more scalable approach to network operations using fully software-based Virtualized Network Functions (VNF) in Core Networks (CN) rather than the prior hardware-based approach. However, while this shift towards a fully software-based system design provides numerous significant benefits, such as increased interoperability, scalability, and cost-effectiveness, it also brings with it an increased cybersecurity risk. Security is crucial to maintaining trust between vendors, operators, and consumers. Cyberattacks are rapidly increasing in number and sophistication, and we are seeing a shift towards zero-trust approaches. This means that even communications between VNFs inside a 5G core must be scrutinized and hardened against attacks, especially with the advent of quantum computers. The National Institute of Standards and Technology (NIST), over the past 10 years, has led efforts to standardize post-quantum cryptography (PQC) to protect against quantum attacks. This paper covers a custom implementation of the open-source free5GC CN, to expand its HTTPS capabilities for VNFs by introducing PQC Key Encapsulation Methods (KEM) for Transport Layer Security (TLS) v1.3. This paper provides the details of this integration with a focus on the latency of different PQC KEMs in initial handshakes between VNFs, on packet size, and the implications in a 5G environment. This work also conducts a security comparison between the PQC-equipped free5GC and other open-source 5G CNs. The presented results indicate a negligible increase in UE connection setup duration and a small increase in connection setup data requirements, strongly indicating that PQC KEM’s benefits far outweigh any downsides when integrated into 5G and 6G core services. To the best of our knowledge, this is the first work incorporating PQC into an open-source 5G core. Furthermore, the results from this effort demonstrate that employing PQC ciphers for securing VNF communications results in only a negligible impact on latency and bandwidth usage, thus demonstrating significant benefits to 5G cybersecurity.