Article
Automation & Control Systems
Mohsen Jorjani, Hossein Seifi, Ali Yazdian Varjani
Summary: The article introduces a new algorithm for detecting false data injection attacks (FDIAs) using outlier detection techniques on state estimation results and a graph-theory-based approach to detect potential attacks, and the algorithm demonstrates satisfactory performance in detecting both types of FDIAs in IEEE 14 bus and 118 bus test systems.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Electrical & Electronic
Shuheng Wei, Junjun Xu, Zaijun Wu, Qinran Hu, Xinghuo Yu
Summary: This paper proposes a novel FDIA detection strategy for unbalanced distribution networks by introducing SE model and general imperfect FDIA to simulate attacking behavior. A square-root unscented Kalman filter (SR-UKF) based forecasting-aided SE (FASE) is proposed to achieve FDIA detection. By modifying the filtering step into a redundant linear regression form, random outliers can be effectively detected and suppressed by leveraging the projection statistics. A generalized likelihood ratio test (GLRT) is designed to detect FDIAs on consecutive snapshots by comparing the dynamic time warping (DTW) distance between two innovation sequences with the offline determined detection threshold. Extensive numerical simulations validate the feasibility of the proposed general imperfect FDIA and the effectiveness of the FDIA detection strategy.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Computer Science, Theory & Methods
Moulik Choraria, Arpan Chattopadhyay, Urbashi Mitra, Erik G. Strom
Summary: This study examines the design of false data injection attacks on a distributed cyber-physical system, utilizing a stochastic process with linear dynamics and Gaussian noise. The attack involves manipulating sensor observations and messages among agent nodes to steer estimates towards a specified value while maintaining attack detection probability constraints.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Yapei Gu, Xiang Yu, Kexin Guo, Jianzhong Qiao, Lei Guo
Summary: This paper investigates safety issues of unmanned aerial vehicles (UAVs) under the false data injection attack (FDIA) through wireless data link, including analysis of attack characteristics, proposal of attack detection mechanism, compensation for FDIA impact on UAV dynamics, and demonstration of the effectiveness of the proposed methods through simulation examples.
INFORMATION SCIENCES
(2021)
Article
Automation & Control Systems
Hao Liu, Ben Niu, Yuzhe Li
Summary: This article studies a security issue in remote distributed consensus estimation, where sensors transmit their measurements to remote estimators via a wireless communication network. The relative entropy is used as a metric to detect data attacks, and the false-data attack strategy by an attacker is characterized to achieve the maximal integrated mean-square error.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Automation & Control Systems
Li Li, Huan Yang, Yuanqing Xia, Li Dai
Summary: This paper investigates a distributed secure estimation problem for a nonlinear stochastic system subject to false data injection attack. A novel protector is designed for each sensor to resist hostile attack, and a dynamic decision rule is developed to reduce data receiving frequency. The paper establishes sufficient conditions to ensure bounded estimation error and discusses the critical attack probability for the steady-state estimation error exceeding a preset value.
Article
Automation & Control Systems
Wenying Xu, Zidong Wang, Liang Hu, Juergen Kurths
Summary: This article addresses the security issues in the state estimation problem for a networked control system (NCS) by proposing a new model of joint false data injection (FDI) attack and providing easy-to-implement algorithms. By investigating the sparsity of the attack vectors, necessary conditions for insecurity under different attack scenarios are derived. The effectiveness of the proposed FDI attacks is verified through numerical examples.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Engineering, Electrical & Electronic
Haosen Yang, Xing He, Ziqiang Wang, Robert C. Qiu, Qian Ai
Summary: This paper proposes a blind FDIA approach against the state estimation of power grids based on matrix reconstruction and subspace estimation. It overcomes the shortcoming of previous methods in handling measurement noise with limited data. The proposed method demonstrates high successful rate of FDIA and great robustness to large-scale power grids and high-level measurement noise.
IEEE TRANSACTIONS ON SMART GRID
(2022)
Article
Automation & Control Systems
Haibin Guo, Jian Sun, Zhong-Hua Pang, Guo-Ping Liu
Summary: This article aims to devise an efficient scheme on false data-injection (FDI) attacks to degrade the performance of remote state estimation. A stealthy FDI attack mechanism is introduced to selectively inject false data while evading an anomaly detector. The performance degradation is evaluated using the state estimation error covariance, and an optimal strategy is presented to maximize the trace of the state estimation error covariance under attack stealthiness constraints. Simulation experiments demonstrate the superiority of the proposed method compared with existing ones.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Energy & Fuels
Ge Cao, Rong Jia, Jian Dang
Summary: The stable operation of microgrids requires immediate communication and accurate measuring data. The cyber security of smart grids involves detection and mitigation, but traditional methods have limited application in microgrids. This study proposes a mitigation framework based on local detection and resilient control to enhance the cyber security of microgrids.
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Engineering, Electrical & Electronic
Claudio Burgos-Mellado, Claudio Zuniga-Bauerle, Diego Munoz-Carpintero, Yeiner Arias-Esquivel, Roberto Cardenas-Dobson, Tomislav Dragicevic, Felipe Donoso, Alan Watson
Summary: Implementing control schemes for Modular Multilevel Converters (M2Cs) involves cyber and physical aspects, resulting in a Cyber-Physical System (CPS). This article focuses on False Data Injection Attacks (FDIAs) on M2Cs, where the control system receives corrupted data due to illegitimate intrusions. It proposes a reinforcement learning-based method to expose the deficiencies of existing FDIA detectors and provides valuable information to enhance the detectors' performance.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2023)
Article
Engineering, Electrical & Electronic
Zhixun Zhang, Jianqiang Hu, Jianquan Lu, Jinde Cao, Jie Yu
Summary: The development of integrated energy system has led to the emergence of the largest and most complex cyber-physical energy system. The openness of the load frequency control system has made it vulnerable to false data injection attacks. This paper presents an artificial intelligence-based strategy to detect and counteract these attacks, using LM-BP neural networks to analyze historical data and replace traditional control methods with LM-BP NNs to mitigate the effects of FDIAs, as demonstrated in interconnected power systems.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Automation & Control Systems
Yi Hua, Fangyi Wan, Hongping Gan, Youmin Zhang, Xinlin Qing
Summary: A conveniently distributed diffusion least-mean-square (DLMS) algorithm with cross-verification (CV) is proposed against false data-injection (FDI) attacks. The proposed DLMS-CV algorithm improves detection performance and addresses the problem of data tampering in FDI attacks through a CV mechanism and adaptive threshold design.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Energy & Fuels
Junjun Xu, Zaijun Wu, Tengfei Zhang, Qinran Hu, Qiuwei Wu
Summary: This paper proposes a novel secure forecasting-aided state estimation framework for power distribution systems with high penetration of renewable energy, addressing the impact of false data injection attacks on state estimation. By constructing a FASE model and combining the sliding time window theory and optimal state forecasting strategy, the compromised measurements introduced by potential attacks can be corrected effectively.
Article
Engineering, Marine
Hong Zeng, Yuanhao Zhao, Tianjian Wang, Jundong Zhang
Summary: This paper proposes a defense strategy to detect and mitigate false data injection attacks on ship direct current microgrids. By training an artificial neural network model and comparing the error between estimated and measured values with a threshold generated from history data, the method successfully identifies and mitigates false data injection attacks.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.