CSE DSI Machine Learning Seminar with Hanshen Xiao (CSAIL, MIT)

PAC Privacy: Automatic Privacy Measurement and Control of Data Processing

In this talk, I will introduce a new privacy definition, termed Probably Approximately Correct (PAC) Privacy. PAC Privacy characterizes the information-theoretic hardness to recover sensitive data given arbitrary information disclosure/leakage during/after any processing. Unlike the classic cryptographic definition and Differential Privacy (DP), which consider the adversarial (input-independent) worst case, PAC Privacy is a simulatable metric that quantifies the instance-based impossibility of inference. A fully automatic analysis and proof generation framework are proposed: security parameters can be produced with arbitrarily high confidence via Monte-Carlo simulation for any black-box data processing oracle. This appealing automation property enables analysis of complicated data processing, where the worst-case proof in the classic privacy regime could be loose or even intractable. Moreover, we show that the produced PAC Privacy guarantees enjoy simple composition bounds and the automatic analysis framework can be implemented in an online fashion to analyze the composite PAC Privacy loss even under correlated randomness. On the utility side, the magnitude of (necessary) perturbation required in PAC Privacy is not lower bounded by Theta(\sqrt{d}) for a d-dimensional release but could be O(1) for many practical data processing tasks, which is in contrast to the input-independent worst-case information-theoretic lower bound. I will also talk about practical applications to complicated data processing, including end-to-end privacy analysis of deep learning and clustering.

Hanshen Xiao is a final-year PhD student in MIT, advised by Srini Devadas. His research interests lie at the intersection of the fundamental of information security, statistical learning and applied cryptography. He received the B.S. degree in Mathematics from Tsinghua University and is the recipient of several awards, including Mathwork Fellowship (2021-2023) and Tsinghua Future Scholar Fellowship (2015-2017). His work is also supported by DSTA Singapore and Capital One Research Award.