In this article, we propose a planning-operation coordinated mitigation scheme for load redistribution (LR) attacks to overcome the deficiencies of separately designed phase shifting transformer-based mitigation strategies. Specifically, the interactions amongst the defender, attacker, and system are formulated as a trilevel optimization, where the deployment of defense devices and phase shift angles can be optimized according to possible operation state. Based on the proposed load similarity metric, a clustering-based approximate solution is designed to reduce the computational complexity caused by the integration of planning and operation stages. Simulation results on the IEEE 14-bus and 30-bus test systems verify the performance of the proposed mitigation scheme and the clustering-based approximate solution method.

In privacy-preserving mobile network transmission scenarios with heterogeneous client data, personalized federated learning methods that decouple feature extractors and classifiers have demonstrated notable advantages in enhancing learning capability. However, many existing approaches primarily focus on feature space consistency and classification personalization during local training, often neglecting the local adaptability of the extractor and the global generalization of the classifier. This oversight results in insufficient coordination and weak coupling between the components, ultimately degrading the overall model performance. To address this challenge, we propose FedeCouple, a federated learning method that balances global generalization and local adaptability at a fine-grained level. Our approach jointly learns global and local feature representations while employing dynamic knowledge distillation to enhance the generalization of personalized classifiers. We further introduce anchors to refine the feature space; their strict locality and non-transmission inherently preserve privacy and reduce communication overhead. Furthermore, we provide a theoretical analysis proving that FedeCouple converges for nonconvex objectives, with iterates approaching a stationary point as the number of communication rounds increases. Extensive experiments conducted on five image-classification datasets demonstrate that FedeCouple consistently outperforms nine baseline methods in effectiveness, stability, scalability, and security. Notably, in experiments evaluating effectiveness, FedeCouple surpasses the best baseline by a significant margin of 4.3%.

Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To address these limitations, we propose FedMate(Code: https://github.com/Dongrun-Li/FedMate.git. Full version of this paper can be found in [39].), a method that implements bilateral optimization: On the server side, we construct a dynamic global prototype, with aggregation weights calibrated by holistic integration of sample size, current parameters, and future prediction; a category-wise classifier is then fine-tuned using this prototype to preserve global consistency. On the client side, we introduce complementary classification fusion to enable merit-based discrimination training and incorporate cost-aware feature transmission to balance model performance and communication efficiency. Experiments on five datasets of varying complexity demonstrate that FedMate outperforms state-of-the-art methods in harmonizing generalization and adaptation. Additionally, semantic segmentation experiments on autonomous driving datasets validate the method’s real-world scalability.

Modern power systems benefit from enhanced reliability and efficiency due to advanced information technologies, but face increased cyber vulnerabilities, particularly false data injection attacks (FDIAs) that threaten grid stability. We propose a Transformer-Gated Recurrent Unit (TGRU) framework, integrating Transformer encoders’ feature extraction with GRUs’ temporal modeling. A novel Euclidean distance-based threshold selection method distinguishes legitimate from malicious data, and an FDILocator module accurately identifies attack locations by analyzing discrepancies between TGRU predictions and actual measurements. Experiments on the IEEE 14-bus system validate the approach’s effectiveness and accuracy.

State estimation methods in smart grids are vulnerable to false data injection attacks (FDIAs). To address this threat, recent research has adopted deep neural networks (DNNs) to detect such attacks. However, DNNs exhibit inherent security flaws, making their decisions susceptible to adversarial perturbations. Exploiting this vulnerability, adversarial FDIAs have been designed to evade DNN-based detection. In this paper, we propose a black-box adversarial false data injection attack leveraging autoencoders. The attack uses an autoencoder to learn the underlying physical model of grid data without prior knowledge of the network topology or detection mechanisms. This is jointly optimized with a surrogate model to generate adversarial perturbations. Experimental results demonstrate that the proposed attack successfully evades both conventional bad data detectors and DNN-based detectors, achieving high success rates in black-box settings. This vulnerability poses a significant security threat to smart grids.

Differential privacy is widely employed in decentralized learning to safeguard sensitive data by introducing noise into model updates. However, existing approaches that use fixed-variance noise often degrade model performance and reduce training efficiency. To address these limitations, we propose a novel approach called decentralized learning with adaptive differential privacy via variance-reduced stochastic gradient push (ADP-VRSGP). This method dynamically adjusts both the noise variance and the learning rate using a stepwise-decaying schedule, which accelerates training and enhances final model performance while providing node-level personalized privacy guarantees. To counteract the slowed convergence caused by large-variance noise in early iterations, we introduce a progressive gradient fusion strategy that leverages historical gradients. Furthermore, ADP-VRSGP incorporates decentralized push-sum and aggregation techniques, making it particularly suitable for time-varying communication topologies. Through rigorous theoretical analysis, we demonstrate that ADP-VRSGP achieves robust convergence with an appropriate learning rate, significantly improving training stability and speed. Experimental results validate that our method outperforms existing baselines across multiple scenarios, highlighting its efficacy in addressing the challenges of privacy-preserving decentralized learning.

With the merging of the Internet of Things and artificial intelligence, the data becomes valuable stuff and can be traded between utilities. Unfortunately, low-value data and conflicting interests among participants hinder the progress of data trading. To facilitate trading, assessing the data value and balancing the interests of each party gained widespread attention. In this article, we propose a value-guaranteed data trading approach using a three-stage Stackelberg game (SG), i.e., fair data trading approach (FDTA). Specifically, a consignment contract is negotiated between the trusted platform and data providers, which helps to release the cost of sale for both parties. A data-value quantification approach is developed based on the data size, completeness, and usability. Combined with the consignment contract, the data value is transparent to all parties before trading. Furthermore, a three-stage SG model is constructed to simulate the interactions between the trusted platform, data provider, and data consumer regarding data value. The trusted platform and data provider are the leaders, while the consumer is the follower. Besides, we prove that there is a unique Nash equilibrium in this game, ensuring that the interests of all participants are balanced. Finally, we conduct extensive experiments to evaluate the performance of FDTA. The results show that FDTA can effectively guarantee the effectiveness of data-value assessment and the fairness of trading.

Load frequency control (LFC) is usually managed by traditional proportional–integral–derivative (PID) controllers. Recently, deep reinforcement learning (DRL)-based adaptive controllers have been widely studied for their superior performance. However, the DRL-based adaptive controller exhibits inherent vulnerability due to adversarial attacks. To develop more robust control systems, this study conducts a deep analysis of DRL-based adaptive controller vulnerability under adversarial attacks. First, an adaptive controller is developed based on the DRL algorithm. Subsequently, considering the limited capability of attackers, the DRL-based LFC is evaluated under adversarial attacks using the zeroth-order optimization (ZOO) method. Finally, we use adversarial training to enhance the robustness of DRL-based adaptive controllers. Extensive simulations are conducted to evaluate the performance of the DRL-based PID controller with and without adversarial attacks.

As wind power systems expand in size and complexity, the imperative for cyber security measures becomes increasingly critical, especially in light of the escalating threat posed by the zero-dynamics attack. Unfortunately, when the relative degree of a continuous-time system is greater than two and the sampling period is small, the sampled-data system will inevitably introduce unstable zeros, making it vulnerable to attackers. Meanwhile, it is difficult for traditional output-based system monitoring methods to detect such attacks. The current mainstream approach employs the generalized hold or generalized sampler to achieve zero shifting, but the implementation is challenging. In this article, we propose a defense method based on electronically tunable passive components to address this challenge. The method effectively defends against the zero-dynamics attack by introducing a gain-scheduling combined with the real-time parameter adjustment function of the electronically tunable passive components to move the unstable zeros of the system. Simulation results show that this defense method can improve the ability of the wind power system to resist zero-dynamics attack.

Federated learning (FL) is an effective mobile edge computing framework that enables multiple participants to collaboratively train intelligent models, without requiring large amounts of data transmission while protecting privacy. However, FL encounters challenges due to non-independent and identically distributed (non-IID) data from different participants. The existing methods, whether focusing on local training or global aggregation, often suffer from insufficient unilateral optimization. Achieving effective local-global collaborative optimization, particularly in the absence of additional reference models or datasets, is both crucial and challenging. To address this, we propose a novel approach:Dual-AggregatedFederated learning based on a tripleSiamese network (FedSiam-DA). This method enhances the FL algorithm on both client and server sides. On the client side, we establish a triple Siamese network incorporating a stop-gradient scheme, which leverages a contrastive learning strategy to control the update directions of local models. On the server side, we introduce a dual aggregation mechanism with dynamic weights for local updates, improving the global model’s ability to assimilate personalized knowledge from local models. Extensive experiments on multiple benchmark datasets demonstrate that FedSiam-DA significantly improves model performance under non-IID data conditions compared to existing methods.

With the widespread application of collaborative learning (CL) technology in mobile-crowdsourcing-related scenarios, special attention should be paid to the privacy disclosure problem therein. Many pioneer noise-perturbation-based methods, particularly the differentially private ones, provide only homogeneous protection, which is insufficient for the heterogeneous protection requirements of many practical CL cases. In this article, we propose a privacy-aware mechanism that uses appropriate Gaussian noises to obfuscate the local and aggregated models. The noise variance is determined based on clients’ different privacy requirements. By zero-concentrated differential privacy, we analyze clients’ privacy-preserving degrees (PPDs) in the uplink and downlink channels. The obtained PPDs demonstrate that the information received by the aggregating server and the peer clients has distinct preservation effects, indicating that our scheme achieves the goal of heterogeneous protection. Moreover, we conduct a theoretical analysis of the performance of the global models aggregated during the iterative process. Finally, we validate the correctness of our theory with experimental results using a real-world data set.

Distributed classification learning (DCL) is a promising solution to establish Internet of Things-based smart applications, especially due to its strong ability in dealing with large-scale and high-concurrency data. However, the performance of DCL may be seriously affected by the label flipping attack (LFA). Regarding the LFA-resilient learning problem, most existing works are built in more centralized settings. The work addressing the secure DCL issue makes an assumption that the label flipping rates are symmetric and available for scheme design. In this article, we remove this assumption and propose an LFA-resilient DCL scheme, named FENDER, without knowing the asymmetric flipping rates. The challenge is to guarantee both attack resilience and algorithm convergence. We carefully integrate a resilient loss and the alternating direction method of the multiplier scheme, making FENDER resilient to LFA. Further, we systematically analyze the performance of FENDER according to a metric reflecting the models obtained by all the servers at different iterations. In addition, we discuss and compare FENDER with some existing methods from the aspects of algorithm establishment and performance guarantee. Finally, extensive experiments with multiple real-world data sets are performed to validate the developed theory and evaluate the performance of the trained models.

Collaborative computing is efficient to conduct large-scale computation tasks, especially with the surge in data volume. However, when the data contains sensitive information, privacy has to be attached significant attention during the execution of computation tasks. In this paper, based on a two-step average computation framework, we first propose three different privacy-aware schemes, where noises are carefully designed to be injected into the distributed computing process. The challenging issue is to guarantee the privacy loss in each iteration to be controllable and quantifiable, which we call the dynamic privacy-preserving collaborative computing problem. By employing Kullback-Leibler differential privacy, we obtain the privacy preserving levels in different iterations regarding the three schemes, followed by the analysis of their convergence performances. Further, we devise an approach to balance the privacy loss and the computation accuracy, whose challenge lies in how to motivate data contributors (DCs) to report more accurate data without providing them with monetized payments. This is done by allowing DCs to report data multiple times, and we obtain the optimal reporting times for each DC. Finally, extensive numerical experiments are performed to validate the obtained theoretical results.

The leakage of driving positions or traces poses a serious privacy threat upon the users in the vehicular ad-hoc networks (VANETs). A series of pseudonym changing approaches have been proposed to achieve unlinkability between the users' identities and their driving information. To investigate the effectiveness of the changing strategies on user anonymity, it is important to stand at the side of an adversary to implement posterior linking between different pseudonyms. In this paper, we remove the assumption of motion models commonly used in existing works, and propose a novel pseudonym linking scheme by focusing on the prediction of acceleration and direction angle. Further, we plug several side information (e.g., road structure, traffic signal) into the proposed scheme to improve the linking performance. Finally, based on five representative pseudonym changing strategies, extensive experiments are conducted to evaluate the performance of the proposed linking scheme. The experimental results show that the side-information assisted pseudonym linking scheme achieves success rates of over 74%.