Elliptic Envelope Based Detection of Stealthy False Data Injection Attacks in Smart Grid Control Systems

Ashrafuzzaman, Mohammad; Das, Saikat; Jillepalli, Ananth A.; Chakhchoukh, Yacine; Sheldon, Frederick T.

doi:10.1109/ssci47803.2020.9308523

Cited by 11 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Slightly different trends were observed in the case of the other metrics like Precision, Recall, Sensitivity, and F1 score in the case of both Clustered and Linear Datasets. Several models that had previously had moderate and semi-moderate accuracy now had either high precision, recall, or F1 score, despite the ordering hierarchy being relatively constant as these models were geared towards linear data when compared to clustering data as shown in FIGURE 10,11,12.…”

Section: B Results For Linear Datamentioning

confidence: 99%

“…Jillepalli, Yacine Chakhchoukh, Mohammad Ashrafuzzaman, Saikat Das, Ananth A., Frederick T. Sheldon. [12] The authors create and test an unsupervised machine intelligence strategy called Elliptical Envelope.…”

Section: Youguomentioning

confidence: 99%

“…Isolation forest provides us with an algorithm through which we can partition the dataset features in order to identify the outliers which exceed the defined range [10], [11]. The Elliptic envelope model tends to create an ellipse around the scatter plot for the dataset and all points lying outside its boundaries signify the outliers present in the dataset [12], [13]. Another approach involving plotting and analyzing histograms is the Histogram based algorithm for outlier detection (HBOD) method which is also an effective unsupervised method to detect anomalies.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PAACDA: Comprehensive Data Corruption Detection Algorithm

et al. 2023

View full text Add to dashboard Cite

With the advent of technology, data and its analysis are no longer just values and attributes strewn across spreadsheets, they are now seen as a stepping stone to bring about revolution in any significant field. Data corruption can be brought about by a variety of unethical and illegal sources, making it crucial to develop a method that is highly effective to identify and appropriately highlight the various corrupted data existing in the dataset. Detection of corrupted data, as well as recovering data from a corrupted dataset, is a challenging problem. This requires utmost importance and if not addressed at earlier stages may pose problems in later stages of data processing with machine or deep learning algorithms. In the following work we begin by introducing the PAACDA: Proximity based Adamic Adar Corruption Detection Algorithm and consolidating the results whilst particularly accentuating the detection of corrupted data rather than outliers. Current state of the art models, such as Isolation forest, DBSCAN also called "Density-Based Spatial Clustering of Applications with Noise" and others, are reliant on fine-tuning parameters to provide high accuracy and recall, but they also have a significant level of uncertainty when factoring the corrupted data. In the present work, the authors look into the most niche performance issues of several unsupervised learning algorithms for linear and clustered corrupted datasets. Also, a novel PAACDA algorithm is proposed which outperforms other unsupervised learning benchmarks on 15 popular baselines including K-means clustering, Isolation forest and LOF (Local Outlier Factor) with an accuracy of 96.35% for clustered data and 99.04% for linear data. This article also conducts a thorough exploration of the relevant literature from the previously stated perspectives. In this research work, we pinpoint all the shortcomings of the present techniques and draw direction for future work in this field.

show abstract

Section: B Results For Linear Datamentioning

confidence: 99%

Section: Youguomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PAACDA: Comprehensive Data Corruption Detection Algorithm

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Detecting features is usually aimed at determining whether some specific characteristics are present within the data or not. The following one-class classifiers as depicted in Figure 2 were trained on legitimate websites features: Isolation Forest [11], Local Outlier Factor [12], Mahalanobis Classifier [13], Elliptical Envelope [14], Minimum Covariance Determinant [15], and One-Class Support Vector Machine (OCSVM) [16]. These individual weak classifiers were represented as Ci for each weak classifier.…”

Section: Hybrid Feature Detectionmentioning

confidence: 99%

PhisNet: Deep learning-based Hybrid and Ensemble Multi-level Approach for the detection of phishing websites

Soni,

Prabakar,

Upadhyay

2024

Preprint

View full text Add to dashboard Cite

Phishing is a cyber-attack that intends to trick individuals into providing an attacker with sensitive information, such as login authorizations or business information. One tactic that attackers use is creating fake websites that mimic legitimate ones to fool victims into entering their information. A learning-based model can be used to analyze patterns in website content, structure, behavior, email text, sender, and links. These models can help identify phishing attempts and protect individuals and organizations from falling victim to these scams. In this research, we study and experiment with the deep learning-based algorithm in classifying phishing webpages from legitimate webpages that can be generalized across multiple domains. We used the open-source benchmark dataset, "Phishing Dataset for Machine Learning," available on Kaggle. We propose a hybrid and a multi-level ensemble approach for phishing website detection. Several one-class classifiers are trained on the first level, and the Variational Autoencoder (VAE) is used to reduce the size of feature vectors. Each one class classifiers have its own strength and limitations, and thus an adaptive weightage approach is applied. At the second level, a multilayer neural network is trained for classification. Further, the training time is reduced due to feature reduction in the latent space. Our experimental results classify phishing websites from legitimate websites with 98% accuracy.

show abstract

“…However, their study was conducted almost 10 years ago, and it is not clear if it still holds on recent attack types. Elliptic Envelopes [4], another unsupervised anomaly detection method, it has been used by the authors of [15] to detect Injection Attacks in Smart Grid Control Systems.…”

Section: Related Workmentioning

confidence: 99%

Towards Intrusion Detection Of Previously Unknown Network Attacks

Alzubi¹,

Stahl²,

Gaber³

2021

ECMS 2021 Proceedings Edited by Khalid Al-Begain, Mauro Iacono, Lelio Campanile, Andrzej Bargiela

View full text Add to dashboard Cite

Advances in telecommunication network technologies have led to an ever more interconnected world. Accordingly, the types of threats and attacks to intrude or disable such networks or portions of it are continuing to develop likewise. Thus, there is a need to detect previously unknown attack types. Supervised techniques are not suitable to detect previously not encountered attack types. This paper presents a new ensemble-based Unknown Network Attack Detector (UNAD) system. UNAD proposes a training workflow composed of heterogeneous and unsupervised anomaly detection techniques, trains on attack-free data and can distinguish normal network flow from (previously unknown) attacks. This scenario is more realistic for detecting previously unknown attacks than supervised approaches and is evaluated on telecommunication network data with known ground truth. Empirical results reveal that UNAD can detect attacks on which the workflows have not been trained on with a precision of 75% and a recall of 80%. The benefit of UNAD with existing network attack detectors is, that it can detect completely new attack types that have never been encountered before.

show abstract

Elliptic Envelope Based Detection of Stealthy False Data Injection Attacks in Smart Grid Control Systems

Cited by 11 publications

References 24 publications

PAACDA: Comprehensive Data Corruption Detection Algorithm

PAACDA: Comprehensive Data Corruption Detection Algorithm

PhisNet: Deep learning-based Hybrid and Ensemble Multi-level Approach for the detection of phishing websites

Towards Intrusion Detection Of Previously Unknown Network Attacks

Contact Info

Product

Resources

About