Boris Köpf

About

I am a researcher in the Confidential Computing group at Microsoft Research Cambridge, working on techniques for tracking information flow in microarchitecture and machine learning systems. Prior to joining MSR in November 2018, I was a tenured faculty at the IMDEA Software Institute, a postdoc at the Max Planck Institute for Software Systems, and a Ph.D. student at ETH Zurich.

Recent Work

Microarchitectural Security

Hide and Seek with Spectres: Efficient discovery of speculative information leaks with random testing (S&P '23) [pdf]
Revizor: Testing Black-box CPUs against Speculation Contracts (ASPLOS '22) [pdf][git]
Hardware-Software Contracts for Secure Speculation (S&P '21) [pdf]
Spectector: Principled Detection of Speculative Information Flows (S&P '20) [pdf][git]
(more)

Privacy-preserving Machine Learning

SoK: Let The Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning (arXiv) [pdf]
Bayesian Estimation of Differential Privacy (arXiv) [pdf]
Grey-box Extraction of Natural Language Models (ICML '21) [pdf]
Analyzing Information Leakage of Updates to Natural Language Models (CCS '20) [pdf]
(more)

Upcoming Events

USENIX Security 2023 (PC member)
SaTML 2023, IEEE Conference on Secure and Trustworthy Machine Learning (PC member)
S&P 2023, IEEE Symposium on Security and Privacy (PC member)
NUS Computer Science Research Week 2022 (speaker)
Summer School on Real-World Crypto and Privacy 2022 (speaker)
(more)

Contact

email: boris.koepf@microsoft.com