More Like this

1. Detecting Cyber Attacks in Smart Grids Using Semi-Supervised Anomaly Detection and Deep Representation Learning

   https://doi.org/10.3390/info12080328  

   Qi, Ruobin; Rasband, Craig; Zheng, Jun; Longoria, Raul (August 2021, Information)

   null (Ed.)

   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
2. Self-Supervised Learning for Online Anomaly Detection in High-Dimensional Data Streams

   https://doi.org/10.3390/electronics12091971  

   Mozaffari, Mahsa; Doshi, Keval; Yilmaz, Yasin (May 2023, Electronics)

   In this paper, we address the problem of detecting and learning anomalies in high-dimensional data-streams in real-time. Following a data-driven approach, we propose an online and multivariate anomaly detection method that is suitable for the timely and accurate detection of anomalies. We propose our method for both semi-supervised and supervised settings. By combining the semi-supervised and supervised algorithms, we present a self-supervised online learning algorithm in which the semi-supervised algorithm trains the supervised algorithm to improve its detection performance over time. The methods are comprehensively analyzed in terms of computational complexity, asymptotic optimality, and false alarm rate. The performances of the proposed algorithms are also evaluated using real-world cybersecurity datasets, that show a significant improvement over the state-of-the-art results. 

   more » « less
3. AutoOD: Automatic Outlier Detection

   https://doi.org/10.1145/3588700  

   Cao, Lei; Yan, Yizhou; Wang, Yu; Madden, Samuel; Rundensteiner, Elke A. (May 2023, Proceedings of the ACM on Management of Data)

   Outlier detection is critical in real world. Due to the existence of many outlier detection techniques which often return different results for the same data set, the users have to address the problem of determining which among these techniques is the best suited for their task and tune its parameters. This is particularly challenging in the unsupervised setting, where no labels are available for cross-validation needed for such method and parameter optimization. In this work, we propose AutoOD which uses the existing unsupervised detection techniques to automatically produce high quality outliers without any human tuning. AutoOD's fundamentally new strategy unifies the merits of unsupervised outlier detection and supervised classification within one integrated solution. It automatically tests a diverse set of unsupervised outlier detectors on a target data set, extracts useful signals from their combined detection results to reliably capture key differences between outliers and inliers. It then uses these signals to produce a "custom outlier classifier" to classify outliers, with its accuracy comparable to supervised outlier classification models trained with ground truth labels - without having access to the much needed labels. On a diverse set of benchmark outlier detection datasets, AutoOD consistently outperforms the best unsupervised outlier detector selected from hundreds of detectors. It also outperforms other tuning-free approaches from 12 to 97 points (out of 100) in the F-1 score. 

   more » « less
4. Using Machine Learning to Aid in Data Classification: Classifying Occupation Compatibility with Highly Automated Vehicles

   https://doi.org/10.1177/1064804620923193  

   Kamaraj, Amudha_V; Lee, John_D (May 2020, Ergonomics in Design: The Quarterly of Human Factors Applications)

   Data classification is central to human factors research, and manual data classification is tedious and error prone. Supervised learning enables analysts to train an algorithm by manually classifying a few cases and then have that algorithm classify many cases. However, algorithms often fail to leverage human insight. To address this, we augment supervised learning with unsupervised learning and data visualization. Unsupervised learning highlights potential classification errors, explains the underlying classification, and identifies additional cases that merit manual classification. We illustrate this using the Occupational Information Network database to classify occupations as having tasks that might be performed in an automated vehicle. 

   more » « less
5. A Review of Human Immune Inspired Algorithms for Intrusion Detection Systems

   https://doi.org/10.1109/AIIoT54504.2022.9817213  

   Duru, Chukwuemeka; Ladeji-Osias, Jumoke; Wandji, Ketchiozo; Otily, Toutsop; Kone, Rachida (June 2022, 2022 World AI IoT Congress (AIIOT))

   Security and trust of Information Systems are critical in its design as they directly influence users' view and acceptance of such systems. Security can be said to be a contextual and dynamic term as there has not been a holistic, universal, and eternal security measure to date. Recent years have seen a lot of confidential and sensitive information being sent, received, and analyzed on the Internet, and a plethora of investigations on ways of developing comprehensive security solutions like encryptions, pattern recognition, and anomaly detection. This work reviews the human inspired algorithms that are particularly employed in pattern recognition and anomaly detection problems. The work discusses the components of the immune system that inspired the artificial Immune System (AIS) based algorithms for pattern and intrusion detection (IDS) problems. A detailed comparison is made between negative selection, clonal selection, and dendritic cell algorithms (danger theory) which are the three major AIS algorithms. AIS is ubiquitous in computer and information security because it is based on the theories developed through years of study and understanding of the human immune system by immunologist. The strengths and weaknesses of these algorithms are also discussed, and possible improvement suggested. 

   more » « less