Synthetic data generation has emerged as a promising approach to address challenges related to data scarcity, privacy constraints, and bias mitigation in machine learning applications. In networking, especially intrusion detection systems (IDS), access to balanced and unbiased datasets is critical for developing robust models. However, real-world network traffic datasets often exhibit significant class imbalance and encode discriminatory patterns across sensitive attributes, which can result in unfair decision-making. This paper proposes FairTabFormer, a transformer-based generative model tailored to produce realistic, fair, tabular synthetic network traffic data. Based on the GPT-2 decoder architecture, FairTabFormer integrates a fairness-aware training paradigm that penalizes disparity in prediction distributions across sensitive groups, specifically targeting protocol types in intrusion detection datasets. The model leverages a custom loss function that combines cross-entropy with fairness regularization, ensuring demographic parity in the generated data. The experimental evaluation uses the CIC IoT23 dataset, a comprehensive benchmark for IoT-based threat detection. The downstream performance is assessed using an XGBoost classifier using accuracy as the primary utility metric, while fairness is measured using the Demographic Parity Ratio (DPR) and the Demographic Parity Difference (DPD). Comparative results against state-of-the-art models such as CTGAN and REaLTabFormer demonstrate that FairTabFormer achieves superior fairness while maintaining high predictive utility. These findings underscore its potential to enhance fairness without compromising data quality.

Network slicing is the critical enabler for next-generation mobile networks, which divides the infrastructure into multiple logical networks known as slices. Each logical network supports services with specific throughput and latency requirements. The fifth-generation(5G) and 5G-beyond networks employ more than two slices; hence, it has become necessary to deploy algorithms for efficient resource allocation. However, given the latency-sensitive applications, allocating resources to different slices based on the current demand would be a poor choice. Therefore, resource allocation needs to be performed in advance, which calls for forecasting algorithms predicting future demands. In this paper, we propose a novel predictive network slicing mechanism named NPRA to predict resources dynamically. NPRA predicts the future resource requirements using Unit Time Long Short-Term Memory (UT-LSTM). The predicted demand can be used as an input to any optimization algorithm for the timely allocation of resources. We also develop a 5G simulation testbed to generate datasets for performance study. The results presented demonstrate the effectiveness of NPRA.

Network Function Virtualization (NFV) has become a promising technology, which is used to replace the complex hardware implementation of various Network Functions. Virtual Network Functions (VNFs) are placed on the servers to realize these functions of a network, for example 5G network. Such an implementation reduces the expenditure and latency significantly. However, it also comes with its own set of challenges. One of the prominent challenges of NFV is the placement problem. The requests are in the form of a Service Function Chain (SFC), which is a pre-defined sequence of VNFs. When an SFC request comes in, resources must be allocated to the VNF instances to satisfy the requirements. In this paper, we propose an effective algorithm D3T (Double Deep Q-Network Decision Transformer) to optimize the SFC placement. The algorithm is designed using a Decision Transformer (DT) that is assisted by a Double Deep Q-Network (DDQN). We employ a DDQN model as the baseline algorithm to generate offline training data. The trajectory data in the Experience Reply Memory of DDQN will be processed into sequences and modeled by a transformer. The algorithm’s objective function considers end-to-end delay and rejection ratio as the objectives. Specifically, D3T combines the transformer with DRL to give an optimal solution. The results presented demonstrate the effectiveness of the proposed solution.

The keyless entry systems in cars enable users to lock or unlock cars remotely. One of the popular types of keyless entry systems used in cars is the Remote Keyless Entry (RKE) system. With the advent of quantum computers, quantum computing-enabled cyber-attacks are an imminent threat. The security offered by current cryptographic techniques is inadequate to protect systems such as RKE from such future quantum attacks. In this paper, we propose a quantum-safe authentication protocol leveraging Quantum Key Distribution (QKD) that authenticates a legitimate key fob before unlocking the car. We present a formal security proof and an informal analysis to show that the protocol is secure against several attacks. To the best of our knowledge, this is the first protocol that protects RKE systems from future quantum computing-enabled cyber-attacks, in addition to the existing replay and RollJam attacks.

Electric Vehicle (EV) adoption has been increasing in recent years due to multiple factors. Though EVs offer many advantages, the cyber security of EV networks is often overlooked. When individuals charge their EVs at charging stations, the communication between the EV and the other components of the charging system is through the Internet. It is crucial to understand the potential attacks that an attacker could launch and propose solutions to prevent such attacks to safeguard the EV networks. In this paper, we address message tampering attacks on EV networks and propose a mechanism to prevent them. Existing solutions for message tampering are not suitable for EV networks due to the high computation cost and latency requirements. In the proposed solution, EVs generate authentication parameters based on the charging requests they transmit. The authentication parameters are delivered to a central server together with the charging requests. This enables the server to verify the integrity of the received charging requests. Since the proposed mechanism does not include computationally expensive operations, it does not add significant cost. We present a formal security proof to show that the proposed mechanism provides protection from message tampering attacks and achieves several security properties in the EV charging framework. A performance analysis is also presented to show the computation cost of the proposed mechanism.

The use of unmanned aerial vehicles (UAVs) for diverse activities has increased rapidly in recent years. Nonetheless, if operational cyber security is not handled effectively, these technologies offer a significant hazard which can cause catastrophic harm. Therefore, it is important to identify the potential attacks that can be implemented by an adversary. Traditional methods for data integrity designed for the Internet are not suitable for UAV assisted vehicular or wireless sensor networks due to the high communication overhead and latency required. This paper proposes a lightweight data integrity technique called MaDe to address this problem. Every device, at regular intervals, generates an authentication parameter that depends on the packets transmitted. The authentication parameters are only delivered to a central server or the device where the integrity of the packets is verified. At the server, MaDe takes the final decision about an UAV using a generalized likelihood ratio test. MaDe can identify malicious UAVs effectively as demonstrated through our performance analysis. The results show that MaDe detects malicious UAVs with minimum communication overhead and latency.

The Internet of Vehicles (IoV) may enhance road safety, improve traffic flow, etc. However, Internet-connected intelligent vehicles (IVs) are vulnerable to cyber-attacks. One of the important challenges in IoV is thus, verifying data integrity with strict latency requirements. The conventional way of providing data integrity in the Internet cannot be applied to IoV due to excessive overhead and latency. Therefore, most commercially available IVs do not use any security mechanisms for delay-sensitive traffic. However, if a road side unit (RSU) has been compromised, it can tamper with the data sent or received by IVs. To solve this issue, this article presents a light-weight mechanism called DRiVe to establish data integrity for the IVs and detect malicious RSUs. The DRiVe is based on a probabilistic model to identify malicious RSUs using specially constructed authentication techniques. The authentication parameters are only sent when a vehicle leaves the coverage area of one RSU and enters that of another. DRiVe does not employ any computationally intensive cryptographic primitives. This significantly reduces the security overhead introduced by sending message authentication codes (MACs) with each packet. A security and performance analysis shows that DRiVe can not only identify malicious RSUs effectively but can do so without introducing any significant communication overhead or latency. The proposed scheme reduces the number of bits transmitted by approximately 7% and decreases the latency incurred by 7.5%. For the scenario where malicious vehicles are present, the proposed scheme achieves a probability of detection close to 99%.

Compromised relays in clustered IoT networks can be used to launch attacks that cannot be easily detected using the traditional security algorithms. In this paper, we consider an attack where a compromised relay deliberately drops the packets received from the IoT devices it serves. Such an attack causes the IoT devices to retransmit more frequently, thereby increasing their processing load. As a result, their batteries will drain at a faster rate. The difficulty in differentiating a genuine packet drop event from a malicious packet drop event makes it necessary to develop a novel Intrusion Detection System (IDS) specially tailored for detecting such an attack. The IDS is installed in a special node called a sentinel, which monitors the network. The sentinel also estimates the packet retransmission rate of the IoT devices, a parameter required for the IDS. The effectiveness of the system is demonstrated experimentally on a clustered network.

Clustering Internet of Things (IoT) networks, to alleviate the network scalability problem, provides an opportunity for an adversary to compromise a set of nodes by simply compromising the relay they are associated with. In such scenarios, an adversary who has compromised the relay can affect the network's performance by deliberately dropping the packets transmitted by the IoT devices and/or by corrupting the packets to be forwarded by the relay. In this way, the adversary can successfully mimic a bad radio channel between the IoT devices and the relay, thereby requiring the IoT devices to retransmit more frequently. Such a strategy increases the processing load on the IoT devices and will drain their batteries at a faster rate. To detect such an attack, we present hybrid intrusion detection systems that rely on the monitoring of uplink and downlink packets transmitted between IoT devices and the relay. Specifically, we compare the observed packet drop probabilities against their long-term expected values. The detection rules proposed originate from the generalized likelihood ratio test, where the adversary parameters are estimated using maximum likelihood estimation. A semi-analytical approach to obtain the expressions for the false alarm probability is presented in order to determine the decision thresholds. Results presented show the effectiveness of the proposed detection systems, demonstrate the impact of the choice of adversary parameters on them, and validate the expressions obtained for the false alarm probability.

Mobile Edge Computing can be used to realize the low latency requirements of vehicular networks. However, by compromising the road side units (RSUs), an adversary can introduce an extra delay leading to various problems such as the wastage of edge computing resources and disruption of navigational and safety functions. The compromised RSU can for instance deliberately corrupt the PHY layer payload of the packets to be transmitted to the vehicles. With this simple attack, the adversary would increase latency and through that effect, create serious disruptions. Such an attack can affect many critical delay sensitive applications such as collision avoidance. To detect the presence of such an adversary, we propose a trust based detection system in this paper. Each vehicle transmits a feedback packet about every RSU it has interacted with to a central trusted server. Using the feedback obtained from multiple vehicles, at regular intervals, an aggregated trust value for each RSU in the network is obtained and is compared with a threshold to classify the RSU as authentic or malicious. We also present a mechanism to detect the presence of malicious vehicles reporting false feedback in the network. Simulation results presented demonstrate the effectiveness of the proposed detection mechanism and the impact of the choice of adversary parameters on the detection system.