Microsoft Research Summit: Surprising (and unsurprising) Inference Risks in Machine Learning

Here are the slides for my talk at the Practical and Theoretical Privacy of Machine Learning Training Pipelines Workshop at the Microsoft Research Summit (21 October 2021):

The work by Bargav Jayaraman (with Katherine Knipmeyer, Lingxiao Wang, and Quanquan Gu) that I talked about on improving membership inference attacks is described in more details here:

• Bargav Jayaraman, Lingxiao Wang, Katherine Knipmeyer, Quanquan Gu, David Evans. Revisiting Membership Inference Under Realistic Assumptions (PETS 2021).
  [Blog] [Code: https://github.com/bargavj/EvaluatingDPML]

  Read More…

  Microsoft Security Data Science Colloquium: Inference Privacy in Theory and Practice

  1 December 2020 adversarial machine learning, privacy, Bargav Jayaraman, privacy, privacy-preserving machine learning, Microsoft

  Here are the slides for my talk at the Microsoft Security Data Science Colloquium:
  When Models Learn Too Much: Inference Privacy in Theory and Practice [PDF]

  

  The talk is mostly about Bargav Jayaraman’s work (with Katherine Knipmeyer, Lingxiao Wang, and Quanquan Gu) on evaluating privacy:

  • Merlin, Morgan, and the Importance of Thresholds and Priors
  • Evaluating Differentially Private Machine Learning in Practice
  All Posts by Category or Tags.