Ben Y. Zhao

     
portrait

Contact:
ravenben+w at cs dot uchicago dot edu
Twitter, Facebook, Quora, Linkedin.

News in Last 12+ Months

Sept 2021: Voice Cloning paper @ CCS

Congrats to Emily, Max, Christian, Jenna and Angela on their voice cloning attack paper to appear at CCS 2021!

July 2021: MSNBC Interview

on data privacy and deanonymization, video

July 2021: Interview by Time magazine

as part of data privacy article

May 2021: AppBloat paper at TMC

Congrats to Qinge, Qingyuan and the team

May 2021: gave talk at ICLR SecML

on experiences deploying Fawkes image cloaking

Mar 2021: IEEE S&P/Oakland 2022 PC

Mar 2021: Video analytic benchmark at SEC!

Paper on edge analytic benchmark to appear at SEC, congrats to Zhujun and Junchen!

Feb 2021: Physical backdoor at CVPR!

Our paper on backdoor attacks in the wild to appear at CVPR, congrats to Emily, Josephine, Arjun, Kevin!

Jan 2021: HotOS 2021 PC

Dec 2020: NSDI 2022 PC

Dec 2020: EMS authentication at CHI!

User Authentication via EMS paper to appear at ACM CHI, congrats to Yuxin, Zhuolin, Ruben and Pedro!

Nov 2020: CCS 2021 PC

Networking and ML tracks

Sept 2020: Finalist: Innovation by Design Award @FastCompany

Bracelet of silence wins runner-up for Best Experimental Design Award @ FastCompany

Aug 2020: WWW 2021 Senior PC

Aug 2020: Lots of press on Fawkes

New York Times, TheVerge, many others here.

Jul 2020: Fawkes software release

Now available as source, binary for 3 platforms (also .dmg/.exe) here. Current release v0.3

May 2020: Fawkes Image Cloaking paper to appear at USENIX Security

Congrats to Shawn and Emily (co-first authors), Jiayun and Huiying!

Apr 2020: Kevin joins ByteDance Labs

as a researcher on adversarial machine learning! Congrats Kevin!!

CODE

Clickstream modeling code here
Measurement-calibrated graphs here
Embedding graph coordinate systems here

Contact info

Lab: 377 Crerar, Office: 369 Crerar
5730 S. Ellis Ave, University of Chicago
Chicago, IL 60637


Travel/Deadlines (UChicago Calendar)


CFP: Jan 20, 2021 CCS
CFP: February 4, 2021, USENIX Security 2021
CFP: May 6, 2021 CCS

Other Stuff

Google Scholar (~31,000), H-index: 71
Erdos # = 3 (Erdos-M. Saks-K. Hildrum-B. Y. Zhao)
This page, circa 2011

I am a Neubauer Professor of Computer Science at University of Chicago. Over the years, I've followed my own interests in pursuing research problems that I find intellectually interesting and meaningful. That's led me to work on a sequence of areas from P2P networks, online social networks, SDR/open spectrum systems, graph mining and modeling, user behavior analysis, to adversarial machine learning. Since 2016, I've mostly worked on security and privacy problems in machine learning and mobile systems. My meandering interests have led me to publish at a range of top conferences, including Usenix Security/Oakland/CCS, IMC/WWW, CHI/CSCW, and Mobicom/SIGCOMM/NSDI. Here's a wordle of my paper abstracts from 2017-2019.

Together with Prof. Heather Zheng, I co-direct the SAND Lab (Security, Algorithms, Networking and Data) at University of Chicago. I received my PhD in Computer Science from UC Berkeley in 2004, where I was advised by John Kubiatowicz and Anthony Joseph, and created the Tapestry distributed hash table (dissertation). I received my MS from Berkeley in 2000, and my BS in computer science from Yale in 1997. I am an ACM Distinguished Scientist, a recipient of the NSF CAREER award (2005), MIT Tech Review's TR-35 Award (Young Innovators Under 35) (2006), IEEE Internet Technical Committee's Early Career Award (2014), and one of ComputerWorld's Top 40 Technology Innovators under 40. Back when my kids were small and I had "free time," I write about research and PhD life on Quora.

Teaching
Fall 2021: Tu/Th 2PM-3:20PM, Ryerson 277, CS333 Graduate Computer Networking
(Prereq: CMSC 233). This is a course on computer networking specifically designed for graduate students. The course focuses heavily on research methods, and readings focus on technical publications. Undergraduates interested in learning about networking should only take CS333 if they have already completed CS233 or similar as a prerequisite.

Press/Media: A collection of recent news and media coverage of our research, including New York Times articles (by the amazing Kashmir Hill) on our image cloaking tool Fawkes, and our Bracelets of Silence, an ultrasonic, wearable microphone jammer for personal privacy.

Project Links
Fawkes: image cloaking to foil unauthorized face recognition systems, Code/Paper/Video/Media and News
Neural Cleanse: detecting/mitigating backdoors in DNNs, Code/Paper
Bracelets of Silence: restoring personal audio privacy from ubiquitous audio interfaces, Project/papers/code/video.

I'm always looking for bright PhD students!!
I'm always interested in self-driven/passionate students who want to work on high impact projects and have fun doing it. UChicago is a fantastic place to do a PhD, and we're constantly making improvements to the lab and the department. To find out a bit more about me as an advisor, and my views on everything from students to research and the meaning of life, you can read some of my posts on Quora, where I've been "Top Writer" since 2014. To get on a short list of names Heather and I will look for when reviewing applications, please fill out a basic form. This is better than email. I read all my emails. But due to the volume of emails, I am often unable to reply to individual emails.

If you are looking for a summer undergraduate internship, please do not email me directly. UChicago CS has organized a summer undergraduate internship program with more info here. If you are a high school student or undergraduate looking for a summer internship related to data, you might be interested in the CDAC Data and Computing Summer Lab. SAND Lab is involved in both programs, although the number of interns we take each summer can vary depending on the applicant pool.

UChicago Undergraduates interested in research?
We generally advise 3-5 undergraduates in my lab in active research (we're now quite full for 2020). If you're interested in working in my lab as an undergrad, drop me an email. Generally speaking, the best way to join my lab as an undergrad is to take and do well in my courses in networking or applied ML.