I am an associate professor in School of Computing and Information Systems that I joined in early 2020. Prior to joining the University of Melbourne I spent 6 years at Microsoft Research in Cambridge, UK, where I was a principal researcher leading work on Confidential AI and I/O side-channel mitigation. Between 2014 and 2016, I was the Microsoft Fellow at Darwin College in Cambridge University.
My research interests include privacy, integrity and security of machine learning algorithms, data analysis tools, multi-party computation and systems relying on cloud storage, computation and hardware. The goal is to identify and prevent potential vulnerabilities and to design and build efficient solutions with provable guarantees. I also enjoy working on algorithms, data structures and theory.
If you are interested in pursuing a Ph.D. or a Master's project, please contact me directly.
Contact: oohrimenko @ unimelb dоt edu dоt au
News:
- Joint work with a PhD student Jiankai Jin and Eleanor McMurtry and Benjamin I. P. Rubinstein on "Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy Systems" is accepted to IEEE Symposium on Security and Privacy 2022. (pdf) This work led to a fix in Opacus DP library and received Honorable mention on Google's Bug Hunter (link).
- Joint work with Wanrong Zhang and Rachel Cummings "Attribute Privacy: Framework and Mechanisms" is accepted to FAccT 2022.(pdf)
- Joint work with a PhD student Hao Wu and Tony Wirth "Randomize the Future: Asymptotically Optimal Locally Private Frequency Estimation Protocol for Longitudinal Data" is accepted to SIGMOD PODS 2022.(pdf)
- Excited to be a pleanry speaker at AMSI–AustMS Workshop on Bridging Maths and Computer Science in June 2022 in Sydney
- Joint work with a PhD student William Holland and Tony Wirth on oblivious permutations based on Waksman networks accepted to AsiaCCS'22. (code).
- Invited to give a talk at Symposium on Data Access and Privacy, Australian Buareau of Statistics, December 2021.
- Participated in the panel discussion on "Privacy-preserving Machine Learning" at Microsoft Research Summit October 19-21 2021. (video)
- I am a PI on recently awarded joint CATCH MURI-AUSMURI, funded over AUD $8m to convene a team of 16 experts across 7 universities for fundamental discovery in robust human-AI teams for cybersecurity.
- Wanrong Zhang presenting our work on "Attribute Privacy: Framework and Mechanisms" at Foundations of Responsible Computing, FORC 2021 (video, paper)
- Our paper on Leakage of Dataset Properties in Multi-Party Machine Learning with Wanrong Zhang and Shruti Tople was accepted to USENIX Security 2021.
- Co-organising workshop on Privacy-Preserving Machine Learning at ACM CCS 2021. Please consider submitting your work!
- On the PC of AAAI 2022, IEEE S&P 2022 and ACM CCS 2021.
- School of Computing and Information Systems executive member.
- Received Excellence in First-Time Teaching and Learning Award from CIS in 2020.
- Co-organised workshop on Privacy-Preserving Machine Learning at NeurIPS 2020.
- Received Facebook research award on the "Role of applied cryptography in a privacy-focused ecosystem".
- Received Facebook "Probability and Programming research award" with Ben Rubinstein and Toby Murray.