Presented at
DEF CON 32 (2024),
Aug. 10, 2024, 2 p.m.
(240 minutes).
Malware continues to increase in prevalence and sophistication. VirusTotal reported a daily submission of 2M+ malware samples. Of those 2 million malware daily submissions, over 1 million were unique malware samples. Successfully exploiting networks and systems has become a highly profitable operation for malicious threat actors. Traditional detection mechanisms including antivirus software fail to adequately detect new and varied malware. Artificial Intelligence provides advanced capabilities that can enhance cybersecurity. The purpose of this workshop is to provide an immersive, hands on projects that teach security analysts how to train Machine Learning models to detect thousands and thousands of unique malware samples. This workshop delivers a new framework that uses Machine Learning models to analyze malware, produce uniform datasets for additional analysis, and classify malicious samples into malware families. Additionally, this research presents a new Ensemble Classification Facility we developed that leverages several Machine Learning models to enhance malware classification. To our knowledge, this is the first research that utilizes Machine Learning to provide enhanced classification of an entire 200+ gigabyte-malware family corpus consisting of 80K+ unique malware samples and 70+ unique malware families. New, labeled datasets are released to aid in future classification of malware. It is time we leverage the capabilities of Artificial Intelligence and Machine Learning to enhance detection and classification of malware. Topics taught through hands-on projects include Machine Learning, Natural Language Processing, and Deep Learning models. This workshop provides a pathway to incorporate Artificial Intelligence into the automated malware analysis domain.
Presenters:
-
Solomon Sonya
- Computer Science Graduate Student at Purdue University
Solomon Sonya (@0xSolomonSonya) is a Computer Science Graduate Student at Purdue University. He earned his undergraduate degree in Computer Science and Master’s Degrees in Computer Science, Information Systems Engineering, and Operational Strategy. Solomon routinely develops new cybersecurity tools and presents research, leads workshops, and delivers keynote addresses at cyber security conferences around the world. Prior to attending Purdue, Solomon was the Director of Cyber Operations Training. Prior to that position, Solomon was a Distinguished Computer Science Instructor at the United States Air Force Academy, Research Scholar at the University of Southern California, Los Angeles, and an Adjunct Faculty Instructor with the Advanced Course in Engineering Cyberspace Security (ACE) at the Air Force Research Lab in Rome, NY.
Similar Presentations: