Alex Kantchelian

Contact
akant@cs.berkeley.edu

Office Location
795 Soda Hall
UC Berkeley
Berkeley, CA 94720

I'm a PhD student in computer science in my final year, co-advised by Anthony Joseph and Doug Tygar. My research interests lie in Security, Machine Learning, and the intersection thereof. I work in the SCRUB group. I've previously obtained my B.S. from the Ecole Polytechnique, France in 2009 (M1 Engineering of Complex Industrial Systems) and a Master of Information Management and Systems from Berkeley's School of Information in 2011.

Publications

Evasion and Hardening of Tree Ensemble Classifiers
A. Kantchelian, J. D. Tygar, A. D. Joseph
International Conference on Machine Learning (ICML) 2016, June 2016.

Reviewer Integration and Performance Measurement for Malware Detection
B. Miller, A. Kantchelian, S. Afroz, R. Bachwani, R. Faizullabhoy, L. Huang, V. Shankar, M. C. Tschantz, T. Wu, G. Yiu, A. D. Joseph, J. D. Tygar
Detection of Intrusions and Malware & Vulnerability Assessment (DIMVA) 2016, July 2016.

PREDATOR: Proactive Recognition and Elimination of Domain Abuse at Time-Of-Registration
S. Hao, A. Kantchelian, B. Miller, N. Feamster, V. Paxson
In submission.

Better Malware Ground Truth: Techniques for Weighting Anti-Virus Vendor Labels
A. Kantchelian, M. C. Tschantz, S. Afroz, B. Miller, V. Shankar, R. Bachwani, A. D. Joseph, J. D. Tygar
ACM Workshop on Artificial Intelligence and Security (AISec) 2015, October 2015.

Large-Margin Convex Polytope Machine [poster] [code]
A. Kantchelian, M. C. Tschantz, L. Huang, P. L. Bartlett, A. D. Joseph, J. D. Tygar
Neural Information Processing Systems (NIPS) 2014, December 2014.

Adversarial Active Learning
B. Miller, A. Kantchelian, S. Afroz, R. Bachwani, E. Dauber, L. Huang, M. C. Tschantz, A. D. Joseph, J. D. Tygar
ACM Workshop on Artificial Intelligence and Security (AISec) 2014, November 2014.

Approaches to Adversarial Drift
A. Kantchelian, S. Afroz, L. Huang, A. C. Islam, B. Miller, M. C. Tschantz, R. Greenstadt, A. D. Joseph, J. D. Tygar
ACM Workshop on Artificial Intelligence and Security (AISec) 2013, November 2013.

Robust Detection of Comment Spam Using Entropy Rate
A. Kantchelian, J. Ma, L. Huang, S. Afroz, A. D. Joseph, J. D. Tygar
ACM Workshop on Artificial Intelligence and Security (AISec) 2012, October 2012.

Code

My efficient C++11 implementation of the Convex Polytope Machine can be found on my github. It comes with friendly python bindings.

Teaching

In Spring 2012, I was a teaching assistant for the upper undegraduate introduction to CS theory: CS 170 Efficient Algorithms and Intractable Problems (overall teaching effectiveness 4.7/5). In Spring 2014, I was a teaching assistant for CS 70 Discrete Mathematics and Probability Theory (overall teaching effectiveness 4.3/5) which is both a fundamental prerequisite to CS 170 and a beautiful opening to Computer Science. My student evaluations for both classes are available here.

During Summer 2013, I mentored two talented students from BFOIT. I have since then mentored and co-mentored half a dozen bright undergraduate students, three of whom are now graduate students at UC Berkeley.

Activities & Service

In 2015, I have chaired the Adversarial Learning and Social Networks session of the ACM Workshop on Artificial Intelligence and Security (AISec 2015). I have also been a program committee member for AiSec since 2013. In 2014, I was a program committee member for the ICML workshop on Learning, Security and Privacy. In Spring 2013, I was running the Security Reading Group, a weekly lunch meeting which brings together all security students for a thorough discussion around a fresh paper.