Smart grids are facing many challenges including cyber-attacks which can cause devastating damages to the grids. Existing machine learning based approaches for detecting cyber-attacks in smart grids are mainly based on supervised learning, which needs representative instances from various attack types to obtain good detection models. In this paper, we investigated semi-supervised outlier detection algorithms for this problem which only use instances of normal events for model training. Data collected by phasor measurement units (PMUs) was used for training the detection model. The semi-supervised outlier detection algorithms were augmented with deep feature extraction for enhanced detection performance. Our results show that semi-supervised outlier detection algorithms can perform better than popular supervised algorithms. Deep feature extraction can significantly improve the performance of semi-supervised algorithms for detecting cyber-attacks in smart grids
more »
« less
Detecting Cyber Attacks in Smart Grids Using Semi-Supervised Anomaly Detection and Deep Representation Learning
Smart grids integrate advanced information and communication technologies (ICTs) into traditional power grids for more efficient and resilient power delivery and management, but also introduce new security vulnerabilities that can be exploited by adversaries to launch cyber attacks, causing severe consequences such as massive blackout and infrastructure damages. Existing machine learning-based methods for detecting cyber attacks in smart grids are mostly based on supervised learning, which need the instances of both normal and attack events for training. In addition, supervised learning requires that the training dataset includes representative instances of various types of attack events to train a good model, which is sometimes hard if not impossible. This paper presents a new method for detecting cyber attacks in smart grids using PMU data, which is based on semi-supervised anomaly detection and deep representation learning. Semi-supervised anomaly detection only employs the instances of normal events to train detection models, making it suitable for finding unknown attack events. A number of popular semi-supervised anomaly detection algorithms were investigated in our study using publicly available power system cyber attack datasets to identify the best-performing ones. The performance comparison with popular supervised algorithms demonstrates that semi-supervised algorithms are more capable of finding attack events than supervised algorithms. Our results also show that the performance of semi-supervised anomaly detection algorithms can be further improved by augmenting with deep representation learning.
more »
« less
- NSF-PAR ID:
- 10287448
- Date Published:
- Journal Name:
- Information
- Volume:
- 12
- Issue:
- 8
- ISSN:
- 2078-2489
- Page Range / eLocation ID:
- 328
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Electricity theft is a type of cyberattack posing significant risks to the security of smart grids. Semi-supervised outlier detection (SSOD) algorithms utilize normal power usage data to build detection models, enabling them to detect unknown electricity theft attacks. In this paper, we applied feature engineering and ensemble learning to improve the detection performance of SSOD algorithms. Specifically, we extracted 22 time-series and wavelet features from load profiles, which served as inputs for the seven popular SSOD algorithms investigated in this study. Experimental results demonstrate that the proposed feature engineering greatly enhances the performance of SSOD algorithms to detect various false data injection (FDI) attacks. Furthermore, we constructed bagged ensemble models using the best-performing SSOD algorithm as the base model, with results indicating further improvements in detection performance compared to the base model alone.more » « less
-
Anomaly-based attack detection methods that rely on learning the benign profile of operation are commonly used for identifying data falsification attacks and faults in cyber-physical systems. However, most works do not assume the presence of attacks while training the anomaly detectors- and their impact on eventual anomaly detection performance during the test set. Some robust learning methods overcompensate mitigation which leads to increased false positives in the absence of attacks/threats during training. To achieve this balance, this paper proposes a framework to enhance the robustness of previous anomaly detection frameworks in smart living applications, by introducing three profound design changes for threshold learning of time series anomaly detectors:(1) Tukey bi-weight loss function instead of square loss function (2) adding quantile weights to regression errors of Tukey (3) modifying the definition of empirical cost function from MSE to the harmonic mean of quantile weighted Tukey losses. We show that these changes mitigate performance degradation in anomaly detectors caused by untargeted poisoning attacks during training- while is simultaneously able to prevent false alarms in the absence of such training set attacks. We evaluate our work using a proof of concept that uses state-of-the-art anomaly detection in smart living CPS that detects false data injection in smart metering.more » « less
-
null (Ed.)Controllers of security-critical cyber-physical systems, like the power grid, are a very important class of computer systems. Attacks against the control code of a power-grid system, especially zero-day attacks, can be catastrophic. Earlier detection of the anomalies can prevent further damage. However, detecting zero-day attacks is extremely challenging because they have no known code and have unknown behavior. Furthermore, if data collected from the controller is transferred to a server through networks for analysis and detection of anomalous behavior, this creates a very large attack surface and also delays detection. In order to address this problem, we propose Reconstruction Error Distribution (RED) of Hardware Performance Counters (HPCs), and a data-driven defense system based on it. Specifically, we first train a temporal deep learning model, using only normal HPC readings from legitimate processes that run daily in these power-grid systems, to model the normal behavior of the power-grid controller. Then, we run this model using real-time data from commonly available HPCs. We use the proposed RED to enhance the temporal deep learning detection of anomalous behavior, by estimating distribution deviations from the normal behavior with an effective statistical test. Experimental results on a real power-grid controller show that we can detect anomalous behavior with high accuracy (>99.9%), nearly zero false positives and short (<360ms) latency.more » « less
-
While the blockchain technology provides strong cryptographic protection on the ledger and the system operations, the underlying blockchain networking remains vulnerable due to potential threats such as denial of service (DoS), Eclipse, spoofing, and Sybil attacks. Effectively detecting such malicious events should thus be an essential task for securing blockchain networks and services. Due to its importance, several studies investigated anomaly detection in Bitcoin and blockchain networks, but their analyses mainly focused on the blockchain ledger in the application context (e.g., transactions) and targets specific types of attacks (e.g., double-spending, deanonymization, etc). In this study, we present a security mechanism based on the analysis of blockchain network traffic statistics (rather than ledger data) to detect malicious events, through the functions of data collection and anomaly detection. The data collection engine senses the underlying blockchain traffic and generates multi-dimensional data streams in a periodic manner. The anomaly detection engine then detects anomalies from the created data instances based on semi-supervised learning, which is capable of detecting previously unseen patterns, and we introduce our profiling-based detection engine implemented on top of AutoEncoder (AE). Our experimental results support the effectiveness of the presented security mechanism for accurate, online detection of malicious events from blockchain networking traffic data. We also show further reduction in time complexity (up to 66.8% for training and 85.7% for testing), without any performance degradation using feature prioritization compared to the utilization of the entire features.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/info12080328
