Jian Zhang

Associate Professor

Division of Computer Science,
Louisiana State University

358 Hatcher Hall

Tel: (225)-578-8353

Email: zhang at csc dot lsu dot edu

Multi-Perspective Bayesian Learning for Automated Diagnosis of Advanced Malware
NSF IIS-0905478, 2009-2014
Principal Investigator

Contemporary Internet malware is constantly evolving and making antivirus and intrusion detection systems increasingly obsolete. It is no longer acceptable to simply rely on binary signatures for malware identification. Both current and future generations of malware will require entirely new detection strategies that can tolerate the rapid perturbations in binary structure and payload delivery mechanisms. A promising direction to this end is the use of multi-perspective, behavioral-oriented paradigms for malware identification. In this project, we propose a new approach to 1) automatically extract infection knowledge, based on a multi-perspective, behavior-oriented view, and 2) rapidly apply this gained knowledge to diagnose the presence of malware in host computer systems. The research may lead to new complementary strategies for diagnosing malware infections in ways that cannot be defeated through the current suite of antivirus countermeasures.

Building an Intelligent, Uncertainty-Resilient Detection and Tracking Sensor Network
NSF CNS-0963793, 2010-2014
co-Principal Investigator

Detection, identification, and tracking of CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive) plumes can be accomplished by combining the modalities of sensor and cyber networks. The sensor network provides information about physical-space activities, e.g., locations and movements of the plume sources. The cyber network provides storage and computational resources to analyze and infer where the plume originated, the trajectory of its movement, and the prediction of its future movement. The challenges in realizing such a sensor cyber network include intelligent sensing (intelligent sensor selection and coverage) and the capability to deal with uncertainties (uncertainty in measurement as well as in modeling). In this project, we investigate techniques that leverage the convergence between the sensor and the cyber networks to build an intelligent and uncertainty-resilient sensor network.