As the number of electric vehicles on roads significantly increases, spatial-temporal charging coordination mechanisms have been introduced for balancing charging demand and energy supply. However, electric vehicles could send false data, such as state-of-charge (SoC), to the charging coordination mechanism for gaining high charging priority illegally. Machine Learning models can be used to detect false data. However, in our application the detector is trained on a dataset that contains sensitive information, such as the locations and SoC values of the electric vehicles. Therefore, attackers could launch adversarial attacks against the detector, such as membership inference and model inversion, for revealing sensitive information on the drivers whose data are used to train the detector. Furthermore, attackers could launch evasion attacks against the detector by computing false SoC values that are classified benign by the detector. Addressing the three attacks simultaneously makes the problem more complicated because a countermeasure to one attack may degrade the model's accuracy and unintentionally make the model more susceptible to other attacks. Accordingly, in this paper, we propose a deep-learning training approach for false data detector in spatial-temporal charging coordination. Our approach can deal with the tradeoffs and balance the detector's accuracy and robustness against the adversarial attacks. Specifically, our approach combines three techniques, including mimic learning, dropout, and differential privacy, in a certain way that makes the detector highly accurate in detecting false data and also robust against adversarial attacks. To validate our approach, we have conducted a set of experiments and the given results demonstrate the robustness and accuracy of our detector.

The smart grid advanced metering infrastructure (AMI) is vulnerable to electricity theft cyber-attacks in which malicious smart meters report low readings to reduce the consumers’ bills. To avoid this problem, several machine-learning-based detectors have been proposed to detect electricity theft. Most of these detectors are global in the sense that they are trained on different consumption levels, including low and high consumptions, to be used for all consumers. In this article, we introduce a novel type of evasion attacks against global detectors as follows. A malicious consumer who has high consumption level can send false readings for a low-consumption profile (that resembles the profiles the detector is trained on) to evade the detector, i.e., steal electricity without being detected. We first conduct experiments to prove that the existing global detectors are vulnerable to this new kind of evasion attacks. To launch this attack, we train a generative adversarial network (GAN) on a real data set to generate fake low-consumption readings that can evade the detector. The given results indicate that the success rate of the attack is between 82% and 97%. To thwart this attack, we divide the consumers into clusters of close electricity consumption levels and train one detector for each cluster. Therefore, if a malicious consumer in any cluster tries to imitate the consumption profiles of consumers in other clusters, he/she will be detected. On the other hand, it is not profitable to imitate the electricity consumption profiles of consumers in his/her cluster to evade detection. To prove the effectiveness of our countermeasure, extensive experiments are conducted and the results indicate that our countermeasure can successfully thwart the attack.

Energy forecasting is important because it enables infrastructure planning and power dispatching while reducing power outages and equipment failures. It is well-known that federated learning (FL) can be used to build a global energy predictor for smart grids without revealing the customers’ raw data to preserve privacy. However, it still reveals local models’ parameters during the training process, which may still leak customers’ data privacy. In addition, for the global model to converge, it requires multiple training rounds, which must be done in a communication-efficient way. Moreover, most existing works only focus on load forecasting while neglecting energy forecasting in net-metering systems. To address these limitations, in this article, we propose a privacy-preserving and communication-efficient FL-based energy predictor for net-metering systems. Based on a data set for real power consumption/generation readings, we first propose a multidata-source hybrid deep learning (DL)-based predictor to accurately predict future readings. Then, we repurpose an efficient inner-product functional encryption (IPFE) scheme for implementing secure data aggregation to preserve the customers’ privacy by encrypting their models’ parameters during the FL training. To address communication efficiency, we use a change and transmit (CAT) approach to update local model’s parameters, where only the parameters with sufficient changes are updated. Our extensive studies demonstrate that our approach accurately predicts future readings while providing privacy protection and high communication efficiency.

Charging coordination is necessary for the successful integration of the Energy Storage Units (ESUs), including electric vehicles and home batteries, into the smart grid. To coordinate charging, the ESUs should send charging requests including time-to-complete-charging (TCC) and battery state-of-charge (SoC) to the charging controller (CC) for scheduling charging, but these data can reveal sensitive information on the ESUs’ owners such as their locations, when they return home and whether they are on travel. In this article, we propose centralized and decentralized privacy-preserving and collusion-resistant charging coordination schemes for ESUs. In the centralized scheme, ESUs authenticate their requests using anonymous tokens. To thwart linkability attacks where the CC uses TCC and SoC to link requests sent from the same ESU at consecutive time slots, an ESU needs to send multiple charging requests with different TCC and SoC values instead of only one request. In the decentralized scheme, charging is coordinated in a distributed way using a privacy-preserving data aggregation technique. The idea is that each ESU selects some ESUs to act as proxies, and shares a secret mask with each proxy. Then, each ESU adds a mask to its charging request and encrypts it so that by aggregating all requests, all masks are nullified and the total charging demand is known, and then it is used to compute the charging schedules. Due to using masking technique, the scheme is secure against collusion attacks. The results of extensive experiments and simulations confirm that our schemes are efficient and secure, and can preserve ESU owners’ privacy and thwart linkability attacks.

Abstract A free space optics based ring topology that transmits full‐duplex data to four different nodes in the ring is proposed. The link is designed such that the four nodes do not require a local optical source to transmit the uplink data. A wavelength division multiplexed signal composed of four different wavelengths each modulated by the downlink baseband data using differential phase shift keying is transmitted towards the nodes. At each node, the downlink baseband data is extracted and the received optical pulses are remodulated by the uplink baseband data using on‐off keying modulation format. Each node has a data rate of 10 Gbps and is at a distance of 400 m from the consecutive node. The free space optical link is modelled on the basis of Gamma‐Gamma channel model under different turbulence conditions by considering the refractive index structure parameter values of , and . Bit error rate results are obtained for both the downlink and uplink channels. Finally, power budget analysis is presented to demonstrate the robustness of the link under different weather conditions.

Recently, deep learning-based models are being extensively utilized for steganalysis. However, deep learning models suffer from overfitting and hyperparameter tuning issues. Therefore, in this paper, an efficient θ -nondominated sorting genetic algorithm- ( θ NSGA-) III based densely connected convolutional neural network (DCNN) model is proposed for image steganalysis. θ NSGA-III is utilized to tune the initial parameters of DCNN model. It can control the accuracy and f-measure of the DCNN model by utilizing them as the multiobjective fitness function. Extensive experiments are drawn on STEGRT1 dataset. Comparison of the proposed model is also drawn with the competitive steganalysis model. Performance analyses reveal that the proposed model outperforms the existing steganalysis models in terms of various performance metrics.

Asymmetric Distributed Source-Channel coding (DSC) is considered, where a pair of correlated sources are transmitting to a central node. The distributed scheme is based on Turbo Trellis Coded Modulation (TTCM), where the first source will be channel encoded and then compressed before it is sent over Nakagami-m fading channels. The second source signal, however, is assumed to be available flawlessly at the destination for exploitation as side information for improving the decoding performance of the first source. A wide range of fading scenarios were considered, where reliable communications approaching the Slepian-Wolf Shannon (SW/S) limit were exhibited. Finally, the scheme is capable of adapting to the time-variant short-term correlation between the two sources.

An iterative Joint Source and Turbo Trellis Coded Hierarchical Modulation is introduced for robust context-aware medical image transmission. Lossless source compression as well as Quality of Service (QoS) might be considered as the main constraints in the telemedicine field. Our proposed scheme advocated was design to exploit both the joint source-and-channel iterative decoding and the cooperative structure in order for tackling these requirements. The Source Node (SN) is constituted by a lossless Variable Length Code (VLC) and Turbo Trellis-Coded Modulation (TTCM) which relies on Hierarchical Modulation (HM). The Relay Node (RN) is used to support the transmission of the most important content of the image. Our proposed scheme exhibits a robustness performance over a realistic uncorrelated Rayleigh fading channel, while it outperforms the non-cooperative scheme by 3 dB at asymptotic (error-free) Peak Signal to Noise Ratio (PSNR) value.

An iterative Joint Source and Channel Coded Modulation (JSCCM) scheme is proposed for robust video transmission over two-way relaying channels. The system advocated was designed for improving the throughput, reliability and coverage area compared to that of conventional one-way relaying schemes. We consider a two-user communication system, where the users exchange their information with the aid of a twin-antenna Relay Node (RN). For each user the proposed lossless video scheme is comprised of a Variable Length Code (VLC) encoder and two Turbo Trellis Coded Modulation (TTCM) encoders one at the Source Node (SN) and one at the RN. The spatio-temporal redundancy of the video sequence is exploited for reducing the iterative decoding complexity. The decoding convergence behaviour of the decoder as well as the power sharing ratio between the two SNs and the RN are characterized with the aid of EXtrinsic Information Transfer (EXIT) charts. Our proposed scheme exhibits an SNR gain of 9 dB compared to the non-cooperative scheme, when communicating over Rayleigh fading channels.