Benjamin RubinsteinBenjamin Rubinstein
Associate Professor
School of Computing & Information Systems
The University of Melbourne, Australia 

Email: [firstname].[lastname]@unimelb.edu.au
Office: Room 7.21 Doug McDonell Building

Affiliations:
Associate Investigator, ARC Centre of Excellence for Mathematical & Statistical Frontiers [link]
Academic Fellow, Centre for Business Analytics, Melbourne Business School [link]

LinkedIn  Twitter  GitHub   Scholar  arXiv  ORCID  Find an Expert

Juliet & Ella   Liam   Lachlan

 
Interests: Statistical Machine Learning, Security & Privacy, Databases, Industry Engagement

Position closing 31 Jan 2018: Postdoctoral Research Fellow in Adversarial Machine Learning [job ad link]

Bio: Ben joined the University of Melbourne in 2013 as a Senior Lecturer in Computing and Information Systems (a RAMAP appointee). Previously he gained four years of industry experience in the research divisions of Microsoft, Google, Intel and Yahoo! (all in the US); followed by a short stint at IBM Research Australia. As a full-time Researcher at Microsoft Research, Silicon Valley, Ben shipped production systems for entity resolution in Bing and the Xbox360 (driving huge success accounting for revenues in the $100m's); his research has helped identify and plug side-channel attacks against the popular Firefox browser, and deanonymise an unprecedented Australian Medicare data release, prompting introduction of the Re-identification Offence Bill 2016. He actively researches topics in machine learning, security & privacy, databases such as adversarial learning, differential privacy and record linkage respectively. His work has been recognised through an Australian Research Council DECRA award, and a Young Tall Poppy Science award. Ben earned the PhD in Computer Science from UC Berkeley under Peter Bartlett in 2010, collaborating closely with the SecML group, at the boundary of machine learning and security.

Service

Funding

At the University of Melbourne since Oct'2013, awarded $2.2m in funding of which $1.96m as lead-CI; and $1.1m on a per-CI basis. Funding includes:

Other News

Research Group

  • Postdocs
    • Shen Wang (2016 - ). Probabilistic programming, databases, record linkage.
    • Yi Han (2016 - ). Adversarial machine learning.
  • PhD students
    • Dongge Liu (w Toby Murray 2018 - ). Software fuzzing with machine learning.
    • Leyla Roohi (w Vanessa Teague 2017 - ). Secure storage and private querying for telecommunications metadata.
    • Lingjuan Lyu (w Marimuthu Palaniswami 2016 - ). Privacy in distributed sensing.
    • Neil Marchant (w Aurore Delaigle 2016 - ). Adaptive sampling.
    • Yuan Li (w Trevor Cohn 2015 - ). Bayesian optimisation, NLP.
    • Xunyun Liu (w Raj Buyya, Rodrigo Calheiros 2015 - ). Stream computing.
    • Safiollah Heidari (w Raj Buyya 2015 - ). ML for distributed computing.
    • Yamuna Kankanige (w James Bailey 2015 - ). Liver transplant outcomes, Austin Health
    • Zay Aye - CompSci (w Rao Kotagiri 2014 - ). Learning distance metrics.
  • PhD students - Completed
    • Maryam Fanaeepour - CompSci (w Lars Kulik, Egemen Tanin 2014 - 17). Location data privacy → Postdoc at Duke University
    • Jiazhen He - CompSci (w James Bailey, Rui Zhang 2014 - 17). Education analytics and MOOCs → Postdoc at Univ Melbourne
    • Zuhe Zhang - Maths & Stats (w Sanming Zhou 2014 - 17). Differential privacy in Bayesian statistics → Data Scientist at ANZ Bank
  • Masters students
    • Completed: Rui Hu, Justin Liang, Nouras Fatima, Zhe Lim (2014); Ben Schroeter, Soundarya Mallemarapu (2015); Samuel Jenkins, Xianjing Fan, Si Chen (2016); Zean Qin, Siyu Feng, Dongge Liu, Tolga Ozdogan, Xianzhuo Ren (2017)
  • Interns from Microsoft Research

Teaching

I co-designed several exciting programs offered by my department (within Engineering): the Master of Business Analytics (joint with the Melbourne Business School, QS-list ranked #5 globally and #1 in the Asia-Pacific), the Bachelor of Science major in Data Science and the Master of Data Science (both joint with Maths & Stats within Science). These programs reflect the interdisciplinary nature of machine learning and its allied areas.

Publications

2018

  • Maryam Fanaeepour and Benjamin I. P. Rubinstein, Histogramming Privately Ever After: Differentially-Private Optimisation of Data-Dependent Error Bounds, Proceedings of the 34th International Conference on Data Engineering (ICDE'2018), accepted Dec 2017. [preliminary preprint]
  • Anthony D. Joseph, Blaine Nelson, Benjamin I. P. Rubinstein, and J. Doug Tygar, Adversarial Machine Learning, Cambridge University Press, monograph in press Feb 2017.

2017

2016

2015

2014

2012

2011 

2010

2009

2008

2007

Pre 2007