https://sites.google.com/a/eng.ucsd.edu/rbassily/home/Raef-Bassily.png
 

Raef Bassily

Postdoctoral Fellow 


Department of Computer Science & Engineering, and 

Center for Information Theory & Applications (ITA) 

University of California San Diego.

Ph.D. (University of Maryland - College Park), 2012.

E-mail: rbassily[at]ucsd.edu


About me:

I am a postdoc in Computer Science & Engineering at University of California San Diego and California Institute for Telecommunications and Information Technology (CALIT2). I also hold a joint lecturer position in CSE department at UCSD. Before I joined UCSD, I was a postdoc in CS department at Penn State working with Adam Smith. My research interests are privacy-preserving data analysis, statistical machine learning, and information and coding theory. My research focuses on developing theoretical foundations and practical algorithms for analysis and transmission of information under adversarial conditions. In my work, I have taken an approach that combines new ideas and algorithmic techniques with tools from information theory, statistics, and optimization.

I completed my Ph.D. in Electrical and Computer Engineering at University of Maryland, College Park where I focused on developing rigorous techniques for provable information-theoretic security in communication systems. Before my Ph.D., I had a B.S. and MSc. degrees in Electrical and Computer Engineering and Engineering Mathematics, respectively, from Cairo University, Egypt.

CV 

Research Statement 

News:


Publications

Pre-Prints

.     R. Bassily and Yoav Freund, Typical StabilityarXiv:1604.03336 [cs.LG], Sep. 2016. (In Submission).

.     R. Bassily, K. Nissim, A. Smith, T. Steinke, U. Stemmer, and J. Ullman, Algorithmic Stability for Adaptive Data Analysis. arXiv:1511.02513 [cs.LG], Nov 2015.  Appeared at STOC 2016. (Invited to the Special issue of SICOMP)

.    R. Bassily, A. Smith, T. Steinke, and J. Ullman, More General Queries and Less Generalization Error in Adaptive Data Analysis.  arXiv:1503.04843 [cs.LG], March 2015.

.    R. Bassily and A. Smith, Local, Private, Efficient Protocols for Succinct Histograms.  http://arxiv.org/abs/1504.04686. Appeared at ACM Symposium on Theory of Computing (STOC 2015), Portland, OR, June 2015.

.    R. Bassily, A. Thakurta, and A. Smith, Private Empirical Risk Minimization, Revisited.  arXiv:1405.7085 [cs.LG], 2014.

.     R. Bassily and A. Smith, Causal Erasure Channels.  arXiv:1409.3893 [cs.IT], 2014.

Conferences

     .     R. Bassily, K. Nissim, A. Smith, T. Steinke, U. Stemmer, and J. Ullman, Algorithmic Stability for Adaptive Data Analysis. Proceedings of the 48th Annual ACM SIGACT Symposium on Theory of Computing (STOC 2016), Cambridge, MA, June 2016. (Invited to the Special Issue of SICOMP)

.     R. Bassily and A. Smith,  Local, Private, Efficient Protocols for Succinct Histograms. ACM Symposium on Theory of Computing (STOC 2015), Portland, OR, June 2015.

.     R. Bassily, A. Thakurta, and A. Smith, Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds, IEEE Symposium on Foundations of Computer Science (FOCS 2014), Philadelphia, PA, Oct. 2014, to appear. 

(Also in ICML workshop on learning, security and privacy (presentation only), Beijing, June 2014.)

.     R. Bassily and A. Smith, Causal Erasure Channels, ACM-SIAM Symposium on Discrete Algorithms (SODA 2014), Portland, OR, Jan. 2014.

.     R. Bassily, A. Groce, J. Katz, A. Smith, Coupled-Worlds Privacy: Exploiting Adversarial Uncertainty in Statistical Data PrivacyFOCS 2013, Berkeley, CA, Oct. 2013.

.     R. Bassily and S. Ulukus, Decode-and-Forward Based Strategies for Secrecy in Multiple-Relay Networks, IEEE Wireless Communications and Networking Conference, Paris, France, April 2012.

.     R. Bassily and S. Ulukus, Deaf Cooperation for Secrecy with a Multi-Antenna Helper, 46th Annual Conference on Information Sciences and Systems (CISS), Princeton, NJ, March 2012.

.     R. Bassily and S. Ulukus, Deaf Cooperation for Secrecy in Multipe-Relay Networks, IEEE Globecom, Houston, TX, December 2011.

.     R. Bassily and S. Ulukus, Ergodic Secret Alignment for the Fading Multiple Access Wiretap Channel, IEEE International Conference on Communications, Cape Town, South Africa, May 2010.

.     R. Bassily and S. Ulukus, A New Achievable Ergodic Secrecy Rate Region for the Fading Multiple Access Wiretap Channel, 47th Annual Allerton Conference on Communications, Control and Computing, Monticello, IL, September 2009.

Journal Articles

.     R. Bassily, E. Ekrem, X. He, E. Tekin, J. Xie, M. Bloch, S. Ulukus, A. Yener, Cooperative Security at the Physical Layer: A Summary of Recent Advances, IEEE Signal Processing Magazine, special issue on Signal Processing for Cyber-security and Privacy, 30(5):16-28, September 2013.

.     R. Bassily and S. Ulukus, Deaf Cooperation and Relay Selection Strategies for Secure Communication in MultipleRelay NetworksIEEE Transactions on Signal Processing, 61(6):1544-1554, 2013.

.     R. Bassily and S. Ulukus, Deaf Cooperation for Secrecy with Multiple Antennas at the Helper, IEEE Transactions on Information Forensics and Security, 7(6):1855-1863, December 2012.

.     R. Bassily and S. Ulukus, Secure Communication in Multiple Relay Networks Through Decode-and-Forward Strategies,  Journal of Communications and Networks, special issue on Physical Layer Security, 14(4):352-363, August 2012.

.     R. Bassily and S. Ulukus, Ergodic Secret Alignment,  IEEE Transactions on Information Theory, 58(3):1594-1611, March 2012.

Recent talks

  • Algorithmic Stability for Adaptive Analysis
    • UCSD, AI Seminar, November 2015.
    • Information Theory and Applications Workshop (ITA 2016), February 2016.
  • New Tools for Privacy-Preserving Statistical Analysis [Slides]
    • Google, Mountain View, CA, March 2015.
    • Yahoo! Labs, Sunnyvale, CA, February 2015.
    • IBM Research, Almaden, CA, February 2015.
  • Local, Private, Efficient Protocols for Succinct Histograms [Slides]
    • Information Theory and Applications (ITA) Workshop, San Diego, CA, February 2015.
  • Private Convex Optimization [Slides]
    • FOCS 2014, Philadelphia, PA, October 2014.
    • Penn State, Theory Seminar, CSE Department, September 2014.
    • CDI Project meeting 2014, Penn State, May 2014.
  • Coding for Causal Adversarial Channels: Between Shannon and Hamming [Slides]
    • Harvard University, CS Theory Seminar, April 2014.
    • SODA 2014, Portland, Oregon, January 2014 (short version).
    • University of California Los Angeles, CS Crypto/Theory Seminar, November 2013.
    • University of California San Diego, ECE Seminar, November 2013.
    • University of Maryland, College Park, Information Theory, Communications, and Control Seminar, ECE Department, October 2013.
  • Coupled-Worlds Privacy: Exploiting Adversarial Uncertainty in Statistical Data Privacy [Slides]
    • Harvard University, Privacy Tools Group, October 2013.
    • Boston University, BU-Security Seminar, CS Department, October 2013.
    • Cornell University, CDI Project meeting, May 2013.

Teaching:

  • Recent classes taught: 
    • Graduate Machine Learning Theory Class (CSE 250C) at University of California, San Diego, Spring 2016. (Click here to access the course page).
  • Lectured three invited lectures on Private Convex Optimization as a part of the Private Data Analysis class (graduate-level) in the CSE Department at Penn State, Spring 2015.
  • Lectured an invited lecture on Randomized Algorithms as a part of the Algorithms Design and Analysis class (graduate-level) in the CSE Department at Penn State, Fall 2014.
  • Teaching Assistant, ECE Department, University of Maryland, College Park:
  • In Spring 2011, I received the Distinguished Teaching Assistant Award for the school year of 2010-2011 from the Center of Teaching Excellence (CTE), University of Maryland, College Park.
  • Teaching Assistant/Lecturer, Department of Engineering Mathematics/Department of Electrical and Computer Engineering, Cairo University, Egypt:
    • Fall 2003 to Spring 2006: I assisted in teaching several undergraduate classes in both Applied Mathematics and Electrical Engineering curricula including: Introduction to Probability Theory, Linear Algebra, Advanced calculus, Systems Theory, and Digital Signal Processing.
    • Summer 2004: I taught a class on Digital Signal Processing and its Applications in Speech and Image Processing at the Department of Electrical and Computer Engineering.