False Data Injection Detection Research Articles

Ensemble LOF-based detection of false data injection in smart grid demand response system

Demand response (DR) systems are prone to false data injection attacks (FDIA), which present substantial economic and operational hazards. Notwithstanding their significance, DR systems are remarkably vulnerable to such vulnerabilities, highlighting the pressing need for improved anomaly detection. In this research, we provide a novel technique called Ensemble Local Outlier Factor (ELOF), specifically designed to identify FDIAs in DR systems. ELOF integrates many local outlier factors (LOF) models with tuned hyperparameters and diverse distance metrics to enhance the identification of harmful activity. By examining an extensive dataset provided by Pecan Street, which encompasses data from 168 houses in Austin, Texas, our methodology outperforms current benchmarks in terms of performance. We also examine the constraints of traditional anomaly detectors, including their susceptibility to noise and biases and their restricted ability to distinguish intricate data patterns. Our investigation uncovers an innovative FDIA vector that enables authorized users to initiate assaults without jeopardizing the integrity of the hardware or communication connections. In addition, we demonstrate how these vectors can be managed for economic benefit through various optimization tactics, highlighting an increasing and noteworthy danger to consumer-focused energy systems. Finally, we show how our model outperforms state-of-the-art detection methods in a smart grid environment, demonstrating our superior technique.

Detection of false data injection in smart grid using PCA based unsupervised learning

Detection of false data injection in smart grid using PCA based unsupervised learning

A Novel Privacy Preserving Scheme for Smart Grid-Based Home Area Networks.

Despite the benefits of smart grids, concerns about security and privacy arise when a large number of heterogeneous devices communicate via a public network. A novel privacy-preserving method for smart grid-based home area networks (HAN) is proposed in this research. To aggregate data from diverse household appliances, the proposed approach uses homomorphic Paillier encryption, Chinese remainder theorem, and one-way hash function. The privacy in Internet of things (IoT)-enabled smart homes is one of the major concerns of the research community. In the proposed scheme, the sink node not only aggregates the data but also enables the early detection of false data injection and replay attacks. According to the security analysis, the proposed approach offers adequate security. The smart grid distributes power and facilitates a two-way communications channel that leads to transparency and developing trust.

Enhancing Power System Cyber-Security With Systematic Two-Stage Detection Strategy

State estimation estimates the system condition in real-time and provides a base case for other energy management system (EMS) applications including real-time contingency analysis and security-constrained economic dispatch. Recent work in the literature shows malicious cyber-attack can inject false measurements that bypass traditional bad data detection in state estimation and cause actual overloads. Thus, it is very important to detect such cyber-attack. In this paper, multiple metrics are proposed to monitor abnormal load deviations and suspicious branch flow changes. A systematic two-stage approach is proposed to detect false data injection (FDI) cyber-attack. The first stage determines whether the system is under attack while the second stage identifies the target branch. Numerical simulations verify that FDI can cause severe system violations and demonstrate the effectiveness of the proposed two-stage FDI detection (FDID) method. It is concluded that the proposed FDID approach can efficiently detect FDI cyber-attack and identify the target branch, which will substantially improve operators' situation awareness in real-time.

Secure and efficient verification for data aggregation in wireless sensor networks

SummaryThe Internet of Things (IoT) concept is, and will be, one of the most interesting topics in the field of Information and Communications Technology. Covering a wide range of applications, wireless sensor networks (WSNs) can play an important role in IoT by seamless integration among thousands of sensors. The benefits of using WSN in IoT include the integrity, scalability, robustness, and easiness in deployment. In WSNs, data aggregation is a famous technique, which, on one hand, plays an essential role in energy preservation and, on the other hand, makes the network prone to different kinds of attacks. The detection of false data injection and impersonation attacks is one of the major concerns in WSNs. In order to verify the data, there is either the end‐to‐end approach or the hop‐by‐hop approach. In the former, the detection of these attacks can only be performed at sink node, i.e., after reception of aggregate, a detection that is inefficient and leads to a significant loss of legitimate data. In this paper, we propose a scheme that provides the end‐to‐end privacy and allows early detection of the attack through a hop‐by‐hop verification, thus reducing the need to rely entirely on sink node for verification. Based on an enhanced version of TinyECC, the solution is implemented on MicaZ and TelosB motes. Through simulation and experimental results, we show the applicability of the scheme for WSNs.

Real-Time Detection of False Data Injection in Smart Grid Networks: An Adaptive CUSUM Method and Analysis

A smart grid is delay sensitive and requires the techniques that can identify and react on the abnormal changes (i.e., system fault, attacker, shortcut, etc.) in a timely manner. In this paper, we propose a real-time detection scheme against false data injection attack in smart grid networks. Unlike the classical detection test, the proposed algorithm is able to tackle the unknown parameters with low complexity and process multiple measurements at once, leading to a shorter decision time and a better detection accuracy. The objective is to detect the adversary as quickly as possible while satisfying certain detection error constraints. A Markov-chain-based analytical model is constructed to systematically analyze the proposed scheme. With the analytical model, we are able to configure the system parameters for guaranteed performance in terms of false alarm rate, average detection delay, and missed detection ratio under a detection delay constraint. The simulations are conducted with MATPOWER 4.0 package for different IEEE test systems.