Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the a...
详细信息
Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d
Extreme events jeopardize power network operations, causing beyond-design failures and massive supply interruptions. Existing market designs fail to internalize and systematically assess the risk of extreme and rare e...
详细信息
The integration of renewable energy resources has made power system management increasingly complex. DRL is a potential solution to optimize power system operations, but it requires significant time and resources duri...
详细信息
In this paper, we present a multi-agent deep reinforcement learning (deep RL) framework for network slicing in a dynamic environment with multiple base stations and multiple users. In particular, we propose a novel de...
详细信息
Beam scanning for joint detection and communication in integrated sensing and communication(ISAC) systems plays a critical role in continuous monitoring and rapid adaptation to dynamic environments. However, the desig...
详细信息
Beam scanning for joint detection and communication in integrated sensing and communication(ISAC) systems plays a critical role in continuous monitoring and rapid adaptation to dynamic environments. However, the design of sequential scanning beams for target detection with the required sensing resolution has not been tackled in the *** bridge this gap, this paper introduces a resolution-aware beam scanning design. In particular, the transmit information beamformer, the covariance matrix of the dedicated radar signal, and the receive beamformer are jointly optimized to maximize the average sum rate of the system while satisfying the sensing resolution and detection probability requirements.A block coordinate descent(BCD)-based optimization framework is developed to address the non-convex design problem. By exploiting successive convex approximation(SCA), S-procedure, and semidefinite relaxation(SDR), the proposed algorithm is guaranteed to converge to a stationary solution with polynomial time complexity. Simulation results show that the proposed design can efficiently handle the stringent detection requirement and outperform existing antenna-activation-based methods in the literature by exploiting the full degrees of freedom(DoFs) brought by all antennas.
In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing a...
详细信息
Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple *** these achieve-ments,LLMs have inherent limitat...
详细信息
Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple *** these achieve-ments,LLMs have inherent limitations including outdated information,hallucinations,inefficiency,lack of interpretability,and challenges in domain-specific *** address these issues,this survey explores three promising directions in the post-LLM era:knowledge empowerment,model collaboration,and model ***,we examine methods of integrating external knowledge into LLMs to enhance factual accuracy,reasoning capabilities,and interpretability,including incorporating knowledge into training objectives,instruction tuning,retrieval-augmented inference,and knowledge ***,we discuss model collaboration strategies that leverage the complementary strengths of LLMs and smaller models to improve efficiency and domain-specific performance through techniques such as model merging,functional model collaboration,and knowledge ***,we delve into model co-evolution,in which multiple models collaboratively evolve by sharing knowledge,parameters,and learning strategies to adapt to dynamic environments and tasks,thereby enhancing their adaptability and continual *** illustrate how the integration of these techniques advances AI capabilities in science,engineering,and society—particularly in hypothesis development,problem formulation,problem-solving,and interpretability across various *** conclude by outlining future pathways for further advancement and applications.
The holomorphic embedding method(HEM)stands as a mathematical technique renowned for its favorable convergence properties when resolving algebraic systems involving complex *** key idea behind the HEM is to convert th...
详细信息
The holomorphic embedding method(HEM)stands as a mathematical technique renowned for its favorable convergence properties when resolving algebraic systems involving complex *** key idea behind the HEM is to convert the task of solving complex algebraic equations into a series expansion involving one or multiple embedded complex *** transformation empowers the utilization of complex analysis tools to tackle the original problem *** the 2010s,the HEM has been applied to steady-state and dynamic problems in power systems and has shown superior convergence and robustness compared to traditional numerical *** paper provides a comprehensive review on the diverse applications of the HEM and its variants reported by the literature in the past *** paper discusses both the strengths and limitations of these HEMs and provides guidelines for practical *** also outlines the challenges and potential directions for future research in this field.
With the exponential rise in global air traffic,ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation *** X-ray baggage monitoring is now standard,...
详细信息
With the exponential rise in global air traffic,ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation *** X-ray baggage monitoring is now standard,manual screening has several limitations,including the propensity for errors,and raises concerns about passenger *** address these drawbacks,researchers have leveraged recent advances in deep learning to design threatsegmentation ***,these models require extensive training data and labour-intensive dense pixelwise annotations and are finetuned separately for each dataset to account for inter-dataset ***,this study proposes a semi-supervised contour-driven broad learning system(BLS)for X-ray baggage security threat instance segmentation referred to as *** research methodology involved enhancing representation learning and achieving faster training capability to tackle severe occlusion and class imbalance using a single training routine with limited baggage *** proposed framework was trained with minimal supervision using resource-efficient image-level labels to localize illegal items in multi-vendor baggage *** specifically,the framework generated candidate region segments from the input X-ray scans based on local intensity transition cues,effectively identifying concealed prohibited items without entire baggage *** multi-convolutional BLS exploits the rich complementary features extracted from these region segments to predict object categories,including threat and benign *** contours corresponding to the region segments predicted as threats were then utilized to yield the segmentation *** proposed C-BLX system was thoroughly evaluated on three highly imbalanced public datasets and surpassed other competitive approaches in baggage-threat segmentation,yielding 90.04%,78.92%,and 59.44%in terms of mIoU on GDXray,SIXray,and Compass-XP,***,the lim
The main role of Automatic Generation Control (AGC) is to maintain power grids frequency within specified operating limits. Due to the fact that AGC is the sole automatic feedback control loop between physical and cyb...
详细信息
暂无评论