Data Integrity Attacks Research Articles

Multiscale Adaptive Multifractal Detrended Fluctuation Analysis-Based Source Identification of Synchrophasor Data

As a typical cyber-physical system, dispersed Phasor Measurement Units (PMUs) are networked together with advanced communication infrastructures to record the Distribution Synchrophasor (DS) which represents the states and dynamics of distribution power networks. Source information of DS is critical for many DS-based applications which is potentially vulnerable to data integrity attacks. To ensure the reliability of DS-based applications, it is imperative to efficiently authenticate the DS source locations before any DS data analytics is initiated. This letter presents a cost-effective method for accurate source identification by realising the multifractality of DS data. First, Multiscale Adaptive Multifractal Detrended Fluctuation Analysis (MSA-MFDFA) is executed to reveal the scale which possesses the most significant multifractality of the time-series DS. Subsequently, Adaptive Multifractal Interpolation (AMFI) is proposed to generate quasi high-resolution DS where unique time-frequency signatures are extracted. Such signatures are further fed into a deep learning model - deep forest for source identification. Experimental results using real-life DS of a distribution network illustrate the excellent performance of the proposed approach.

Resilient Consensus-Based AC Optimal Power Flow Against Data Integrity Attacks Using PLC

This paper investigates the resilience of consensus-based AC optimal power flow (OPF) for distribution networks against the data integrity attacks (DIA). The distribution network is first decomposed into several autonomous microgrids to achieve consensus-based AC OPF through the alternating direction multiplier method (ADMM). Then the vulnerability of consensus-based AC OPF is analyzed by showing how the dispatch results can be easily altered by attackers through falsifying the information (active power, reactive power, and voltage) shared between neighboring microgrids. Two different attack scenarios, viz., economic-driven attacks and disruptive attacks, are studied to show the malicious influence of cyber attacks on consensus-based AC OPF. A detection and mitigation strategy based on the existing power line communication (PLC) infrastructure is then described, where the critical information is not only shared in the cyber layer, but also through the power lines. Game-theoretic analysis is provided to demonstrate the effectiveness of the proposed mitigation strategy. Furthermore, to validate the authenticity of the information through PLC, a physical encryption method based on the Lorenz system is proposed. The effectiveness of the proposed attack-resilient mechanism is verified using the IEEE 123-bus test system.

A coalitional security game against data integrity attacks in autonomous vehicle networks

Autonomous Vehicles (AV) possess an automated driving system that allows the vehicle to respond to external conditions and provide advanced and intelligent transportation services with limited to no human intervention. For AV, the legitimacy and reliability of sensed and transmitted data have direct influence on road network operations. For instance, the integrity of vehicle communications is vulnerable to various threats such as spoofing attacks. Due to the extremely volatile nature of AV, traditional centralized security solutions lack in flexibility and mobility support. Moreover, the very large scale of future AV networks mandates an innovative design of intelligent communications among the vehicles to identify authentic traffic information broadcasted all across the network. In this paper, we design a vehicular collaboration framework that drives the interactions among autonomous vehicles based on trustworthy communications to prevent data integrity attacks. The design involves a distributed, hedonic coalition formation game in which the vehicles evaluate their utilities according to their trust in each other and the data they transmit. The proposed vehicular coalition formation algorithm enables the vehicles to dynamically join and leave the collaborative communities based on trust updates. Vehicles' hybrid trust relationships are derived by integrating the three parameters of the REK model: Reputation, Experience, and Knowledge to optimally exploit the available information in the network and adapt the framework to different road traffic contexts. Furthermore, to protect the formed coalitions against data integrity attacks, a trust-based data aggregation procedure using Dempster-Shafer theory of evidence is adopted to limit the effect of false events on vehicles' decisions. The experimental results show that our collaboration framework is resilient to data corruption and fabrication attacks.

Data Integrity Attacks in Cloud Computing: An Overview of Identifying and Protecting Techniques

Data Integrity Attacks in Cloud Computing: An Overview of Identifying and Protecting Techniques

A Review of Cyber–Physical Security for Photovoltaic Systems

In this article, the challenges and a future vision of the cyber–physical security of photovoltaic (PV) systems are discussed from a firmware, network, PV converter controls, and grid security perspective. The vulnerabilities of PV systems are investigated under a variety of cyberattacks, ranging from data integrity attacks to software-based attacks. A success rate metric is designed to evaluate the impact and facilitate decision-making. Model-based and data-driven methods for threat detection and mitigation are summarized. In addition, the blockchain technology that addresses cyberattacks in software and cybernetworks is described. Simulation and experimental results that show the impact of cyberattacks at the converter (device) and grid (system) levels are presented. Finally, potential research opportunities are discussed for next-generation, cybersecure power electronics systems. These opportunities include multiscale controllability, self-/event-triggering control, artificial intelligence/machine learning, hot patching, and online security. As of today, this study will be one of the few comprehensive studies in this emerging and fast-growing area.

Data Integrity Attack in Dynamic State Estimation of Smart Grid: Attack Model and Countermeasures

A smart grid integrates advanced sensors, efficient measurement methods, progressive control technologies, and other techniques and devices to achieve safe, efficient and economical operation of the grid system. However, the diversified and open environment of a smart grid makes energy and information of the smart grid vulnerable to malicious attacks. As a representative cyber-physical attack, the data integrity attack has an extremely severe impact on the grid operation for it can bypass the traditional detection mechanisms by adjusting the attack vector. In this paper, we first present the attack strategy against dynamic state estimation of power grid in the perspective of adversary and formulate the data integrity attack detection problem that has the characteristic of sequential decision making as a partially observable Markov decision process. Then, a deep reinforcement learning-based approach is proposed to detect against data integrity attacks, which utilizes the Long Short-Term Memory layer to extract the state features of previous time steps in determining whether the system is currently under attack. Moreover, the noisy networks are employed to ensure effective agent exploration, which prevents the agent from sticking to the non-optimal policy. The principle of a multi-step learning is adopted to increase the estimation accuracy of Q value. To address the sparse rewards problem, the prioritized experience replay is proposed to increase training efficiency. Simulation results demonstrated that the proposed detection approach surpasses the benchmarks in the comparison metrics: delay error rate and false rate. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In this paper, we present a deep reinforcement learning-based algorithm to defend against the data integrity attacks of smart grid. Most of the previous works discretized the system states and utilized the current state information to identify whether the system is under attack. For this reason, the detection policy may totally ignored the continuously changing characteristics of the grid states, which will lead to poor detection performance. Moreover, the attacked system states only accounts for a small part of the entire grid operation states, the probability of sampling the experience containing the attack state is extremely small, which limits the learning efficiency of previous RL-based detection approaches. In order to increase the accuracy of detection, we first present the attack strategy against power grid’s dynamic state estimation in the perspective of adversary and formulate the partially observable Markov decision process model of attack detection problem. Moreover, we propose a deep reinforcement learning-based detection approach combining the LSTM network to extract the system state features of the previous time steps to determine whether the system is currently being attacked. To address the sparse rewards problem, the prioritized experience replay is used to increase learning efficiency. The experiments demonstrate the effectiveness of proposed detection scheme compared with benchmarks in terms of detection delay as well as accuracy. In conclusion, the proposed detection scheme is helpful in defending against the data integrity attacks without obtaining the opponent’s strategy in advance and can be conveniently applied to the real-world security management system of smart grid.

Secure Distributed Estimation Against Data Integrity Attacks in Internet-of-Things Systems

A secure distributed estimation method against data integrity attacks is presented for general Internet-of-Things (IoT) systems. By exploiting the spatial sparsity of the attacks, a robust optimal estimation objective to protect the entire IoT system is established. Then, a false data processor is developed to suppress the bad effects of the attacks. The convergence of the presented method is analyzed. It shows that, under accessible conditions, the estimation error will converge to be uniformly bounded for all cases, i.e., all communication links and transmitted data are arbitrarily compromised. Furthermore, by utilizing the property of persistence, a quantitative trust model is established for IoT systems based on the past behaviors of the nodes. Then, a trust-based distributed estimation method is proposed to enhance security. Simulation results by considering an IoT system with 50 nodes and 145 edges are also provided to verify our theoretical results. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The increasingly serious attack events that happened in recent years demonstrate the importance of security in the development of Internet-of-Things (IoT) systems. Different from the traditional Internet, IoT systems are usually constrained by computing and storage resources. Then, complex encryption and authentication algorithms or protocols will not be applicable to IoT systems. Distributed estimation plays an important role in the collaborative control, monitoring, and management of IoT systems. Inevitably, attacks to distributed estimation could make false data spread throughout the networks and further cause terrible consequences, while the issues of network security have not been yet taken into consideration in the existing design of distributed estimation. In this article, we propose a secure distributed estimation method. By adding a security mechanism into the distributed estimation algorithm, the ability of resistance to any data integrity attacks can be achieved. Moreover, the possible damage will be completely controllable for arbitrary attacks. That is, our method can guarantee that the estimation performance will always be acceptable even in the worst case. Besides, it is simple and lightweight, and no additional communication consumption and hardware devices are needed for its deployment and operations.

A Cyber-Secure generalized supermodel for wind power forecasting based on deep federated learning and image processing

Accurate wind power forecasting is one of the most important operations within the economic dispatch problem to increase the performance of power and energy systems. Accordingly, this study proposes a cyber-resilient hybrid approach based on the Federated Learning and Convolutional Neural Network (CNN) procedure for short-term wind power generation forecasting in different regions of Iran. Generalizability, data independence, forecasting for regions where no training data is available, and preserving the security and privacy of data are prominent features of the proposed method. The federated network was designed with an architecture of 9 clients to perform the training process and extract the salient features from the data associated with each region in each client via the CNN technique. Then, the generalized global supermodel is produced based on the extracted features in each client to forecast the wind power in new and unknown regions such as Mahshahr, Bojnord, and Lootak that had no training data available and had no effect on global supermodel generation. Various scenarios were developed to test the robustness of the suggested methodology. In the first scenario, wind power forecasting is performed based on the suggested technique. In this scenario, the accuracy of the generalized supermodel to forecast wind power generation in each of the Mahshahr, Bojnord, and Lootak regions is 84%, 85%, and 74%, respectively. The second scenario models the scaling attack by changing the wind speed parameters to evaluate the performance of forecasting models against the data integrity attack. In this scenario, an evaluation of the forecast results based on various performance metrics is conducted highlighting the accuracy reduction of the forecast model, due to the damage caused by cyber-attacks on the input data. In the third scenario, the detection of cyber-attack is done based on the image processing-based technique. The presented results emphasize the accurate performance and high generalizability of the cyber-resilient global supermodel in forecasting wind power in various regions of Iran.

A robust support vector regression model for electric load forecasting

Electric load forecasting is a crucial part of business operations in the energy industry. Various load forecasting methods and techniques have been proposed and tested. With growing concerns about cybersecurity and malicious data manipulations, an emerging topic is to develop robust load forecasting models. In this paper, we propose a robust support vector regression (SVR) model to forecast the electricity demand under data integrity attacks. We first introduce a weight function to calculate the relative importance of each observation in the load history. We then construct a weighted quadratic surface SVR model. Some theoretical properties of the proposed model are derived. Extensive computational experiments are based on the publicly available data from Global Energy Forecasting Competition 2012 and ISO New England. To imitate data integrity attacks, we have deliberately increased or decreased the historical load data. Finally, the computational results demonstrate better accuracy of the proposed robust model over other recently proposed robust models in the load forecasting literature.

A data quarantine model to secure data in edge computing

&lt;p&gt;Edge computing provides an agile data processing platform for latency-sensitive and communication-intensive applications through a decentralized cloud and geographically distributed edge nodes. Gaining centralized control over the edge nodes can be challenging due to security issues and threats. Among several security issues, data integrity attacks can lead to inconsistent data and intrude edge data analytics. Further intensification of the attack makes it challenging to mitigate and identify the root cause. Therefore, this paper proposes a new concept of data quarantine model to mitigate data integrity attacks by quarantining intruders. The efficient security solutions in cloud, ad-hoc networks, and computer systems using quarantine have motivated adopting it in edge computing. The data acquisition edge nodes identify the intruders and quarantine all the suspected devices through dimensionality reduction. During quarantine, the proposed concept builds the reputation scores to determine the falsely identified legitimate devices and sanitize their affected data to regain data integrity. As a preliminary investigation, this work identifies an appropriate machine learning method, linear discriminant analysis (LDA), for dimensionality reduction. The LDA results in 72.83% quarantine accuracy and 0.9 seconds training time, which is efficient than other state-of-the-art methods. In future, this would be implemented and validated with ground truth data.&lt;/p&gt;

Revealing a New Vulnerability of Distributed State Estimation: A Data Integrity Attack and an Unsupervised Detection Algorithm

This article proposes a distributed false data injection attack (FDIA) by attacking to the boundary buses in an interconnected power system. The proposed attack utilizes the measurements corresponding to a set of boundary buses in each neighboring areas to inject arbitrary errors to the estimated states of those buses. It is demonstrated that the attack not only gets through the robust distributed estimators but also bypasses the convergence-based detection methods. Furthermore, in an illustrative example, the differences in the attack with the conventional FDIA are briefly explained. Then, finding the optimal attack vector to minimize the maximum difference between the per area errors by considering the attacker’s limitations is formulated as a mixed-integer second-order cone programming problem. Finally, an unsupervised machine learning-based detection method is proposed utilizing a kernel density estimation technique along with statistical measures. This follows an outlier detection to filter out attacks. To show the performance of the detector, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$n-1$</tex-math></inline-formula> contingency, which changes the probability distribution of data is analyzed. The proposed attack and detector are tested on various IEEE systems such as IEEE 14-bus and IEEE 118-bus test systems and the results are discussed.

Data Integrity Attacks Against Outage Management Systems

In developed countries, the electric grid and the Internet are societal necessities. In developing countries, both have grown rapidly during the past few decades. The operational benefits from adding digital and communications overlays to the power grid and the resulting coevolution of the two technologies have expose the power systems to potential cyberattacks. The outage management system (OMS) is a crucial component of outage restoration and reliability planning. In this article, we propose a new research topic on data integrity attacks to OMSs. We discuss the scenarios of such attacks, their consequences, and the means to detect and mitigate the attacks. We relate this proposed research topic to the recent progress in three areas, state estimation, load forecasting, and outage prediction. Finally, we discuss the practical challenges and future research directions.

Improved Wasserstein Generative Adversarial Networks Defense Method Against Data Integrity Attack on Smart Grid

Background: As the integration of communication networks with power systems is getting closer, the number of malicious attacks against the cyber-physical power system is increasing substantially. The data integrity attack can tamper with the measurement information collected by Supervisory Control and Data Acquisition (SCADA), which can affect important decisions of the power grid and pose a significant threat to normal operation. Objective: In order to defend against the data integrity attack, and safeguard the normal operation of the power system, we propose a defense method based on improved WGAN (Wasserstein Generative Adversarial Networks). Method: Firstly, through the training of the discriminator and generator, the discriminator identifies and eliminates the measurements damaged by the data integrity attack, and the generator uses the temporal and spatial correlation of the power grid measurements to generate complementary measurements which are infinitely close to the original normal data. Meanwhile, using the improved WGAN, the training stability and the convergence speed are significantly improved, and the quality of complementary data is much higher. Results: Extensive simulation experiments were carried out in the IEEE-14 and IEEE-118 standard bus systems. By comparing the deviations between the complementary data and normal data under different iteration times and methods, the mean squared error of the deviations with the proposed method is greatly reduced than traditional methods. The excellent recovery performance of the defense method based on improved WGAN is verified. Conclusion: A smart grid data integrity attack defense method based on improved WGAN is proposed to detect data integrity attacks, and the experimental results demonstrate the recovery effectiveness of the proposed method.

Data Integrity Attacks in Cloud Computing: A Review of Identifying and Protecting Techniques

Cloud computing is growing tremendously in recent years. Many organizations are switching their traditional computing model to a cloud based because of its low cost and pay-as-you-go manner. Although Cloud Service Provider (CSP) ensures that the data stored in their remote cloud server will be intact and secure. But there are many data integrity issues exist that needed to be addressed. In Cloud environment, lack of data integrity is a major concern. In this paper, we have surveyed several past studies which identifies the issues related to the cloud data storage security such as data theft, unavailability, and data breach of cloud server data. We have also provided a detailed analysis of types of data integrity attacks and their mitigation techniques.

Accuracy improvement of electrical load forecasting against new cyber-attack architectures

• Developing contributions to consider data integrity aspects in load forecasting problem. • Proposing robust schemes to perform accurate load forecasting under new cyber-attacks. • A novel cyber-attack named Civil Attack (CA) is employed to strength the forecasting. • Using accurate non-linear techniques in zones with high load covariance. • Gaussian Process Regression and Random Forest Regression is used to increase accuracy. The cyber challenges faced by cybercriminals are growing dramatically as the power system strives to become more intelligent and more stable. Load forecasting is a well-known problem in the energy management field, but the state-of-the-art lacks contributions that consider data integrity aspects. Despite the existing effective methods on load forecasting, power system requires robust schemes that are also successful in performing accurate load forecasting under cyber-attacks. A novel cyber-attack named Civil Attack (CA) is employed and faced by the two non-linear regression methods. In recent years, numerous regression techniques such as methods called Multiple Linear Regression (MLR), Artificial Neural Network (ANN), Support Vector Regressor (SVR) and etc., were employed to perform electricity load forecasting under false data injection (FDI) attacks. While all of the techniques listed are inaccurate in zones with high load covariance, mostly industrial zones, we propose two non-linear methods called Gaussian Process Regression (GPR) with optimized kernel functions and Random Forest Regression (RFR) to address the problem, while the data integrity attack is used for comparing our methods with other proposed methods.

A Coalitional Security Game Against Data Integrity Attacks in Autonomous Vehicle Networks

A Coalitional Security Game Against Data Integrity Attacks in Autonomous Vehicle Networks

Recovering Missing Data via Top-k Repeated Patterns for Fuzzy-Based Abnormal Node Detection in Sensor Networks

The stream data acquired by heterogeneous Internet of Things (IoT) sensors are seldom perfect. Most of the collected data streams include either missing or abnormal values caused by various factors such as failure, malfunction, or integrity attacks. Such unreliable data affect the real-time monitoring and compromise the quality of data analysis. By simply analyzing the sensor data via anomaly detection, applications may still be unreliable over the incomplete sensor data streams. Therefore, a reliable method for recovering the missing data and detecting the abnormal ones is indispensable in the IoT environment. This paper presents FuzHD++, a new method to recover missing sensor data and detect abnormal nodes jointly rather than independently. Both elements, data recovery and abnormal node detection, rely on the observed temporal and spatial correlation of sensor data to effectively achieve reliable recovery estimation and detection performance. In the data recovery process, the system adopts a matrix profile to extract the top-<i>k</i> repeated patterns from different sensor nodes. Furthermore, it utilizes the <i>k</i>-nearest neighbor estimator to recover the missing data based on the extracted pattern information of multiple neighbor nodes. During the abnormal node detection process, the system adopts a refined fuzzy rule-based detection method. The refined fuzzy rule-based inference system integrates the expert rules and the rules obtained from sensor data analysis to treat the ambiguity in the decision-making process. We validated the performance of FuzHD++ by comparing it with existing methods using two real-world datasets. Our results showed that the proposed missing sensor data recovery method achieves more than 20% improved root mean square error results than most existing methods. Furthermore, FuzHD++ achieved an average accuracy of 92% for analyzing the sensor readings and detecting the abnormal ones. According to the results, the proposed mechanisms based on the observed temporal and spatial correlation analysis improve the robustness of IoT against data loss and integrity attacks.

Fault-Tolerant, Distributed Control for Emerging, VSC-Based, Islanded Microgrids—An Approach Based on Simultaneous Passive Fault Detection

This paper proposes a fault-tolerant control and a robust, distributed, simultaneous, passive fault detection and isolation (or FDI) for islanded ac microgrids (MGs), including heterogeneous distributed generations and battery energy storage systems (BESSs). Disturbances and both actuator and sensor faults are considered in this paper to design a robust distributed control. The nature of the considered faults is general to deal with any sources, e.g., cyber threats (in the form of data integrity attacks) and sensor issues. In this regard, a mixed <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$H_\infty / H_{-}$ </tex-math></inline-formula> formulation is introduced in order to detect and eliminate the undesirable effects of the aforementioned defected components simultaneously, thereby achieving robust performance. Besides, sufficient conditions based on extended linear matrix inequality (also known as LMI) are outlined. Voltage and frequency regulation, active power-sharing, and the state of charge balance of BESSs under faulty conditions are investigated. Different scenarios are tested on a detailed model of a test MG system. The effectiveness of the proposed scheme on mitigating the impacts of faults and disturbances on the distributed energy resources’ (DERs’) performance is evaluated through comprehensive and comparative simulations based on MATLAB/Simulink. Moreover, experimental studies are conducted in order to validate the results in the corresponding practical scenarios.

Image Processing Based Approach for False Data Injection Attacks Detection in Power Systems

With more sensors being installed by utilities for accurate control of power grids, there is a growing risk of vulnerability to sophisticated data integrity attacks such as false data injection (FDI), circumventing current bad data detection schemes resulting in inaccurate state estimation solutions. While diverse automated detectors to battle FDI have been grown, such methodologies underestimate the strong analytical abilities of humans. This is while most proposed automated methods need observant human control. Although automated methods provide opportunities to improve scalability, humans can cope with exceptions and new attack trends. In this paper, to address the ever-increasing cyber-attack challenge in power systems, a visualization based attack detection framework using deep learning techniques is developed to provide human security researchers with improved techniques to uncover trends, identify outliers, recognize correlations, and communicate their results. Specifically, we first encode multivariate systems state time-series data into 2D colored images and then utilize a carefully designed deep convolutional neural network (CNN) classifier. The proposed method is developed to allow network operators to immediately capture and visually understand the statistical features of a network attack at a glance. The proposed method has been evaluated on the IEEE 14-bus and IEEE 118-bus systems. Our experiments show that the proposed framework accomplishes high classification accuracy.

An integrated data-driven scheme for the defense of typical cyber–physical attacks

With the frequent occurrence of safety incidents in cyber–physical systems (CPSs), great significance has been attached to the study of defense schemes against cyber–physical attacks. In this paper, an integrated data-driven defense scheme is proposed, which can sensitively detect data integrity attacks such as false data injection (FDI) attacks, denial-of-service (DoS) attacks, and replay attacks, and ensures secure transmission against eavesdropping attacks. Specifically, a novel deep learning model is designed so that both the online detection task and the encryption/decryption task can be completed under the same framework. The main idea is inspired by denoising auto-encoders whereas necessary changes are made to adapt to the challenges in the context of CPS attacks, and in light of this, the proposed approach is called modified denoising auto-encoder (MDAE). Unlike supervised classifier-based detectors, the proposed detector can retain sensitivity to unknown attacks because it is trained to learn the normal operation behavior. Moreover, to improve the detectability of the DoS and replay attacks on all data, the check code is designed. Encrypting the transmitted data through nonlinear mapping is achieved using the same MDAE, which prevents the attackers from recording useful information. Benefiting from the fact that the dimension of the variables is reduced after encryption, the transmission traffic can be saved. Simulation results on the measurement data instances generated by the IEEE 118-bus system validate the encryption effects and detection accuracy of the proposed scheme and show the superiority by comparison study.