Research

Current Research Topics

Android Malware Classification

We propose a hybrid Android malware classification method based on deep learning and hierarchical multiple kernel learning. We extract several static features and convert them into vector representation. We also record the dynamic system call invocations for each Android application, and convert them into vector and graph representations. The vector sets are fed into deep learning and then combined with graph sets using multiple kernel learning to build the hybrid classifier.

Deep Learning Parallelization on PIMs

The emergence of Processing In Memory (PIM) with die stacking technology presents an opportunity to speed up deep learning computation and reduce energy consumption by providing low-cost high-bandwidth memory accesses. PIM uses 3D die stacking to move computations closer to memory and therefore reduce data movement overheads. We study the parallelization of deep learning methods on a system with multiple PIM devices.

Publications

[Dissertation] Lifan Xu, Android Malware Classification Using Parallelized Machine Learning Methods. Department of Computer and Information Science, University of Delaware, USA, 2016.

Download
[Book Chapter] Lifan Xu, Dongping Zhang, and Dana Schaa, Case Study: Image clustering. In David Kaeli, Perhaad Mistry, Dana Schaa, and Dong Ping Zhang, Heterogeneous Computing with OpenCL 2.0, Chapter 9, pp. 213-228. Morgan Kaufmann Publishers, 2015

Available on Amazon
[Journal] Wei Wang, Lifan Xu, John Cavazos, Howie Huang, Matthew Kay, Fast Acceleration of 2D Wave Propagation Simulations using Modern Computational Accelerators, PLoS ONE 9(1): e86484.doi:10.1371/journal.pone.0086484

Download
[Journal] Giorgos Arampatzis, Markos A. Katsoulakis, Petr Plecháč, Michela Taufer, Lifan Xu, Hierarchical fractional-step approximations and parallel kinetic Monte Carlo algorithms. Journal of Computational Physics, ISSN 0021-9991, 10.1016/j.jcp.2012.07.017.

Download
[Conference] Robert Searles, Lifan Xu, William Killian, Tristan Vanderbruggen, Teague Forren, John Howe, Zachary Pearson, Corey Shannon, Joshua Simmons, John Cavazos, “Parallelization of Machine Learning Applied to Call Graphs of Binaries for Malware Detection.” In Proceedings of the 25th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2017) – St. Petersburg, Russia, 2017.

Download
[Conference] Lifan Xu, Dongping Zhang, Marco A. Alvarez, Jose A. Morales, John Cavazos, “Dynamic Android Malware Classification Using Graph-Based Representations.” In Proceedings of the IEEE International Conference on Cyber Security and Cloud Computing (CSCloud 2016) – Beijing, China, 2016

Download

Dataset
[Conference] Lifan Xu, Dongping Zhang, Nuwan Jayasena, John Cavazos, “HADM: Hybrid Analysis for Detection of Malware.” SAI Intelligent Systems Conference (IntelliSys) 2016 – London, UK, 2016

Download

Dataset
[Workshop] Lifan Xu, Dongping Zhang, Nuwan Jayasena, “Scaling Deep Learning on Multiple In-Memory Processors.” WoNDP: 3rd Workshop on Near-Data Processing In conjunction with MICRO-48 – Waikiki, USA, December, 2015.

Download
[Conference] Dongping Zhang, Nuwan Jayasena, Alexander Lyashevsky, Joseph Greathouse, Lifan Xu, Mike Ignatowski, “TOP-PIM: Throughput-Oriented Programmable Processing in Memory.” In Proceedings of the 23rd International ACM Symposium on High Performance Parallel and Distributed Computing (HPDC'14) – Vancouver, Canada, June, 2014 Best Paper Finalist

Download
[Conference] Dongping Zhang, Lifan Xu, Lee Howes. “Efficient Parallel Image Clustering and Search on a Heterogeneous Platform.” 22nd High Performance Computing Symposium (HPC) 2014 – Tampa, USA, April 2014 Best Paper Award

Download
[Workshop] Lifan Xu, Wei Wang, Marco A. Alvarez, John Cavazos, Dongping Zhang, “Parallelization of Shortest Path Graph Kernels on Multi-Core CPUs and GPUs.” Programmability Issues for Heterogeneous Multicores (MultiProg ‘14) – Vienna, Austria, January, 2014 Best Paper Award

Download
[Conference] Scott Grauer-Gray, Lifan Xu, Robert Searles, Sudhee Ayalasomayajula, John Cavazos, “Auto-tuning a High-Level Language Targeted to GPU Codes.” In Proceedings of Innovative Parallel Computing (InPar'12) – San Jose, USA, May, 2012

Download
[Conference] Lifan Xu, Michela Taufer, Stuart Collins, and Dionisios G. Vlacho, “Parallelization of Tau-Leap Coarse-Grained Monte Carlo Simulations on GPUs.” In Proceedings of the 24th IEEE International Parallel & Distributed Processing Symposium (IPDPS'10) – Atlanta, Georgia, USA, April, 2010

Download
[poster] Lifan Xu, Stuart Collins, Dionisios G. Vlachos, and Michela Taufer, “Parallelization of the Tau-Leap Coarse-Grained Monte Carlo Method for Efficient and Accurate Simulations on GPUs.” Finalist at the ACM Student Research Competition, International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'09) – Portland, Oregon, US

Download

January 2014	Shortest Path Graph Kernel Parallelization
October 2014	Furniture Image Classification
December 2013	Vessel Image Classification
April 2010	Corse-Grained Monte Carlo Simulation Parallelization

Research

Current Research Topics

Android Malware Classification

Deep Learning Parallelization on PIMs

Publications

Projects

Education

University of Delaware

National University of Defense Technology

Resources

Presentations

Code Samples

Contact