Skip to content

Layer 6 AI at ID

  • Blog
  • Publications
  • Careers

TMLR 2024| Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

Transactions on Machine Learning Research
Download PDF

Transactions on Machine Learning Research

TMLR 2024| Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

Authors

  • Jiapeng Wu
  • Atiyeh Ashari Ghomi
  • David Glukhov
  • Jesse C. Cresswell
  • Franziska Boenisch
  • Nicholas Papernot

Related Links

  • Paper
  • Code
  • ArXiv
Download PDF

Abstract

Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified robustness are effective frameworks for combating these two threats respectively, as they each provide future-proof guarantees. However, we show that standard differentially private model training is insufficient for providing strong certified robustness guarantees. Indeed, combining differential privacy and certified robustness in a single system is non-trivial, leading previous works to introduce complex training schemes that lack flexibility. In this work, we present DP-CERT, a simple and effective method that achieves both privacy and robustness guarantees simultaneously by integrating randomized smoothing into standard differentially private model training. Compared to the leading prior work, DP-CERT gives up to a 2.5× increase in certified accuracy for the same differential privacy guarantee on CIFAR10. Through in-depth per-sample metric analysis, we find that larger certifiable radii correlate with smaller local Lipschitz constants, and show that DP-CERT effectively reduces Lipschitz constants compared to other differentially private training methods.

Layer 6

MaRS Discovery District 661 University Ave,Suite 1220Toronto, ON M5G 1M1

We’re hiring!

View current openings careers@layer6.ai info@layer6.ai media@layer6.ai

About TD

General info Privacy Legal
  • LinkedIn
  • X>
  • Github

Layer 6 AI is owned by The Toronto-Dominion Bank. Layer 6 is a trade name of The Toronto-Dominion Bank.

© 2025 The Toronto-Dominion Bank