Published: December 16, 2021
Author(s)
Khandakar Akbar (University of Texas at Dallas), Yingong Wang (University of Texas at Dallas), Md Shihabul Islam (University of Texas at Dallas), Anoop Singhal (NIST), Latifur Khan (University of Texas at Dallas), Bhavani Thuraisingham (University of Texas at Dallas)
Conference
Name: International Conference on Information Systems Security (ICISS 2021)
Dates: December 16-20, 2021
Location: [Virtual] Patna, India
Citation: Information Systems Security, Lecture Notes in Computer Science vol. 13146, pp. 3-25
The cyberworld being threatened by continuous imposters needs the development of intelligent methods for identifying threats while keeping in mind all the constraints that can be encountered. Advanced persistent threats (APT) have become an emerging issue nationwide, in international, and commercial aspects, that secretly steals information and keeps track of system processes over a long period of time. Depending on the objective, adversaries use different tactics throughout the APT campaign to compromise the systems. Therefore, this kind of attack needs immediate attention as such attack tactics are hard to detect for being interleaved with benign activities. Moreover, existing solutions to detect APT attacks are computationally expensive since keeping track of every system behavior is both costly and challenging. In addition, because of the data imbalance issue that appears due to few malicious events compared to the innumerable benign events in the system, the performance of the existing detection models is affected. In this work, we propose novel machine learning (ML) approaches to classify such attack tactics. We convert APT traces into a graph, generate nodes, and eventually graph embeddings, and classify using ML. For ML, we use proposed advanced approaches to address class imbalance issues and compare our approaches with other baseline models and show the effectiveness of our approaches.
The cyberworld being threatened by continuous imposters needs the development of intelligent methods for identifying threats while keeping in mind all the constraints that can be encountered. Advanced persistent threats (APT) have become an emerging issue nationwide, in international, and commercial...
See full abstract
The cyberworld being threatened by continuous imposters needs the development of intelligent methods for identifying threats while keeping in mind all the constraints that can be encountered. Advanced persistent threats (APT) have become an emerging issue nationwide, in international, and commercial aspects, that secretly steals information and keeps track of system processes over a long period of time. Depending on the objective, adversaries use different tactics throughout the APT campaign to compromise the systems. Therefore, this kind of attack needs immediate attention as such attack tactics are hard to detect for being interleaved with benign activities. Moreover, existing solutions to detect APT attacks are computationally expensive since keeping track of every system behavior is both costly and challenging. In addition, because of the data imbalance issue that appears due to few malicious events compared to the innumerable benign events in the system, the performance of the existing detection models is affected. In this work, we propose novel machine learning (ML) approaches to classify such attack tactics. We convert APT traces into a graph, generate nodes, and eventually graph embeddings, and classify using ML. For ML, we use proposed advanced approaches to address class imbalance issues and compare our approaches with other baseline models and show the effectiveness of our approaches.
Hide full abstract
Keywords
advanced persistent threat; online metric learning; data imbalance
Control Families
None selected