UN-AVOIDS: Unsupervised and Nonparametric Approach for Visualizing Outliers and Invariant Detection Scoring

Yousef, Waleed A.; Traoré, Issa; Briguglio, William

doi:10.1109/tifs.2021.3125608

Cited by 12 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, Yousef et al [20] presented UN-AVOIDS in 2021, an unsupervised and nonparametric technique that provides invariant anomalous scores (normalized to [0, 1]) for both viewing and identification of outliers. The key feature of UN-AVOIDS is the transformation of data into a novel space called the Normalized Cumulative Distribution Function (NCDF), where both visualization and detection are performed.…”

Section: Literature Reviewmentioning

confidence: 99%

An Enhanced Outlier Detection Approach for Multidimensional Datasets Using a Synergistic Firefly and Grey Wolf Optimization-Based Method

Govindaraj¹,

Kaliappan²,

Swaminathan³

2023

ISI

View full text Add to dashboard Cite

Outlier identification and elimination are essential preprocessing steps for data analysis tasks such as clustering, classification, and regression. The accuracy of data analysis outcomes may be compromised if outliers are not adequately addressed. Detecting outliers is particularly challenging when they are characterized by unusual combinations of multiple attributes. Furthermore, the presence of outliers can impact various data processing activities, necessitating either the reduction of outlier influence or their complete removal. Outlier detection in multivariate data presents a complex process that becomes increasingly difficult when dealing with high-dimensional datasets. Consequently, this study focuses on the identification of such outliers in multivariate datasets using intelligent techniques. In the proposed approach, outliers are detected using an Improved Neural Network (INN), where the hidden neurons are tuned by a novel Synergistic Firefly-Grey Wolf Optimization (SF-GWO) algorithm. This algorithm combines the strengths of the Firefly Optimization (SFO) and Grey Wolf Optimization (GWO) techniques to maximize accuracy. The unique method results in enhanced classification model performance, reduced computation time, and increased classification accuracy. The proposed model has been evaluated and compared with well-established traditional techniques, demonstrating its effectiveness in addressing the challenges of outlier detection in multidimensional datasets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Enhanced Outlier Detection Approach for Multidimensional Datasets Using a Synergistic Firefly and Grey Wolf Optimization-Based Method

Govindaraj¹,

Kaliappan²,

Swaminathan³

2023

ISI

View full text Add to dashboard Cite

show abstract

“…Traditional defense techniques, such as firewalls and intrusion detection techniques [2,3], typically rely on known attack signatures to identify and match target behaviors, leaving them at a disadvantage against unknown vulnerabilities and backdoors in cyber warfare. A series of novel proactive defense technologies are proposed to address this issue, such as honeypots [4] and Moving Target Defense (MTD) [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Location-Aware Measurement for Cyber Mimic Defense: You Cannot Improve What You Cannot Measure

Huang,

Yuan,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Cyber mimic defense is designed to ensure endogenous security, effectively countering unknown vulnerabilities and backdoors, thereby addressing a significant challenge in cyberspace. However, the immense scale of real-world networks and their intricate topology pose challenges for measuring the efficacy of cyber mimic defense. To capture and quantify defense performance within specific segments of these expansive networks, we embrace a partitioning approach that subdivides large networks into smaller regions. Metrics are then established within an objective space constructed on these smaller regions. This approach enables the establishment of several fine-grained metrics that offer a more nuanced measurement of cyber mimic defense deployed in complex networks. For example, the common-mode index is introduced to highlight shared vulnerabilities among diverse nodes, the transfer probability computes the likelihood of risk propagation among nodes, and the failure risk assesses the likelihood of cyber mimic defense technology failure within individual nodes or entire communities. Furthermore, we provide proof of the convergence of the transfer probability. A multitude of simulations are conducted to validate the reliability and applicability of the proposed metrics.

show abstract

Machine Learning Construction: Implications to Cybersecurity

Yousef

2022

Artificial Intelligence for Cyber-Physical Systems Hardening

View full text Add to dashboard Cite

UN-AVOIDS: Unsupervised and Nonparametric Approach for Visualizing Outliers and Invariant Detection Scoring

Cited by 12 publications

References 43 publications

An Enhanced Outlier Detection Approach for Multidimensional Datasets Using a Synergistic Firefly and Grey Wolf Optimization-Based Method

An Enhanced Outlier Detection Approach for Multidimensional Datasets Using a Synergistic Firefly and Grey Wolf Optimization-Based Method

Location-Aware Measurement for Cyber Mimic Defense: You Cannot Improve What You Cannot Measure

Machine Learning Construction: Implications to Cybersecurity

Contact Info

Product

Resources

About