Abstract :

As Cyberattacks Proliferate Worldwide, It Is Imperative To Figure Tendencies In Those Incidents And Implement Appropriate Countermeasures Expeditiously. The Darknet, An Unutilized IP Address Area, Is Particularly Amenable To The Observation And Analysis Of Indiscriminate Cyberattacks Due To The Lack Of Lawful Connectivity. Malware's Indiscriminate Scanning Actions To Disseminate Infections Frequently Exhibit Analogous Spatiotemporal Patterns, A Phenomenon Additionally Evident On The Darknet. To Address The Issue Of Early Malware Activity Detection, We Deal With The Unusual Synchronization Of Spatiotemporal Styles Visible In Darknet Visitor’s Facts. Our Prior Research Added Algorithms That Autonomously Investigate And Become Aware Of Aberrant Spatiotemporal Patterns Of Darknet Site Visitors In Actual Time The Usage Of 3 Distinct Machine Learning Techniques. This Look At Amalgamated Previously Presented Approaches Into A Unified Framework, Termed Dark-TRACER, And Performed Quantitative Experiments To Assess Its Efficacy In Detecting Malware Interest. We Utilized Darknet Traffic Data From October 2018 To October 2020, Collected Via Our Extensive Darknet Sensors Running At Up To /17 Subnet Sizes. The Findings Indicate That The Deficiencies Of The Tactics Decorate Each Other, And The Proposed Framework Attains A Total Consider Charge Of 100%. Furthermore, Dark-TRACER Identifies Malware Hobby An Average Of 153.6 Days Previous To Their Disclosure By Way Of Esteemed Third-party Security Studies Entities. Ultimately, We Assessed The Cost Of Human Analysis For The Implementation Of The Advised Device And Illustrated That Analysts Can Execute The Daily Operations Required To Manage The Framework In Roughly 7.3 Hours.

Published:

09-6-2025

Issue:

Vol. 25 No. 6 (2025)

Page Nos:

10-13

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite