Guofei Gu

Assistant Professor
Department of Computer Science & Engineering
Texas A&M University
Office: HRBB 502C
Phone: (979) 845-2475
Email: guofei [AT] cse.tamu.edu

I am an assistant professor in the Department of Computer Science & Engineering at Texas A&M University. Before joining Texas A&M, I received my Ph.D. degree in Computer Science from the College of Computing, Georgia Tech, in 2008. I am a recipient of 2010 NSF CAREER award and a co-recipient of 2010 IEEE Symposium on Security & Privacy (Oakland'10) best student paper award. I'm currently directing the SUCCESS (Secure Communication and Computer Systems) Lab at TAMU.

What's

  • [Apr. 2012] Our paper "Bin-Carver: Automatic Recovery of Binary Executable Files" is accepted to DFRWS'12. A new forensics tool "Bin-Carver" is developed to automatically recover deleted or otherwise unreachable executable files.
  • [Jan. 2012] Our paper "Analyzing Spammers' Social Networks For Fun and Profit -- A Case Study of Cyber Criminal Ecosystem on Twitter" is accepted to WWW'12. We have some interesting findings such as that criminal accounts tend to be socially connected, forming a small-world  network. We also revealed several interesting types of criminal support accounts and designed a new criminal account inference algorithm by exploiting their social relationships and semantic coordinations. Congratulations, Chao!
  • [Nov. 2011] Our paper "EFFORT: Efficient and Effective Bot Malware Detection" has been accepted to INFOCOM'12 mini-conference. In this paper, we propose EFFORT, a new host-network cooperated detection framework attempting to combine the best from network-level approaches (efficiency) and host-level approaches (effectiveness) while overcoming their shortcomings. Specifically, we propose a multi-module approach to correlate information from different host- and network-level aspects and design a multi-layered architecture to efficiently coordinate modules to perform heavy monitoring only when necessary.
  • [Nov. 2011] Our paper "Shadow Attacks: Automatically Evading System-Call-Behavior based Malware Detection" will appear in Journal in Computer Virology. In this paper, we present a new class of attacks, namely "shadow attacks", to evade current behavior-based malware detectors by partitioning one piece of malware into multiple "shadow processes". We have developed a compiler-level prototype tool, AutoShadow, to automatically generate shadow-process version of malware given the source code of original malware.
  • [Oct. 2011] Our extended Conficker analysis (ACSAC'10) paper is accepted to IEEE Transactions on Information Forensics and Security.
  • [Sept. 2011] Please consider submitting your paper to a special issue of Computer Networks (Elsevier Journal) on "Botnet Activity: Analysis, Detection and Shutdown"! The deadline is Dec. 1, 2011 extended to Dec. 19, 2011.
  • [Aug. 2011] Our paper "SEMAGE: A New Image-based Two-Factor CAPTCHA" is accepted to ACSAC'11, in which we propose a new explicit-semantic-relationship-based CAPTCHA system to defeat web bots. We have conducted a large-scale user study involving 174 users to gauge and compare accuracy and usability with existing state-of-the-art CAPTCHA systems like reCAPTCHA (text-based) and Asirra (image-based). Nice job, Shardul & Yinan! 
  • New release of BotHunter! Now support Linux/Mac/Windows XP! A live-CD distribution also available!

Research Interests

Selected Recent Publications (a full list)

Conferences in Focus

 Success Lab Students

Teaching

Professional Services

Misc


Free Hit Counter visits since Feb 23, 2004. Last Modified Mar. 2012