Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

• URL: http://arxiv.org/abs/2306.08656v2
• Date: Fri, 19 Jul 2024 20:42:41 GMT
• Title: Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
• Authors: Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, Nicolas Papernot,
• Abstract summary: We show that standard differentially private model training is insufficient for providing strong certified robustness guarantees. We present DP-CERT, a simple and effective method that achieves both privacy and robustness guarantees simultaneously.
• Score: 32.49465965847842
• License: http://creativecommons.org/licenses/by/4.0/
• 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 persample 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. The code is available at github.com/layer6ailabs/dp-cert.

Related papers

• Too Good to be True? Turn Any Model Differentially Private With DP-Weights [0.0]
  We introduce a groundbreaking approach that applies differential privacy noise to the model's weights after training. We offer a comprehensive mathematical proof for this novel approach's privacy bounds. We empirically evaluate its effectiveness using membership inference attacks and performance evaluations.
  arXiv  Detail & Related papers  (2024-06-27T19:58:11Z)
• TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data [50.797729676285876]
  We propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-16T16:41:14Z)
• Sparsity-Preserving Differentially Private Training of Large Embedding Models [67.29926605156788]
  DP-SGD is a training algorithm that combines differential privacy with gradient descent. Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
  arXiv  Detail & Related papers  (2023-11-14T17:59:51Z)
• Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent [69.14164921515949]
  We characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees.
  arXiv  Detail & Related papers  (2022-06-06T13:49:37Z)
• Combining Differential Privacy and Byzantine Resilience in Distributed SGD [9.14589517827682]
  This paper studies the extent to which the distributed SGD algorithm, in the standard parameter-server architecture, can learn an accurate model. We show that many existing results on the convergence of distributed SGD under Byzantine faults, especially those relying on $(alpha,f)$-Byzantine resilience, are rendered invalid when honest workers enforce DP.
  arXiv  Detail & Related papers  (2021-10-08T09:23:03Z)
• Accuracy, Interpretability, and Differential Privacy via Explainable Boosting [22.30100748652558]
  We show that adding differential privacy to Explainable Boosting Machines (EBMs) yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees.
  arXiv  Detail & Related papers  (2021-06-17T17:33:00Z)
• On Deep Learning with Label Differential Privacy [54.45348348861426]
  We study the multi-class classification setting where the labels are considered sensitive and ought to be protected. We propose a new algorithm for training deep neural networks with label differential privacy, and run evaluations on several datasets.
  arXiv  Detail & Related papers  (2021-02-11T15:09:06Z)
• Robustness Threats of Differential Privacy [70.818129585404]
  We experimentally demonstrate that networks, trained with differential privacy, in some settings might be even more vulnerable in comparison to non-private versions. We study how the main ingredients of differentially private neural networks training, such as gradient clipping and noise addition, affect the robustness of the model.
  arXiv  Detail & Related papers  (2020-12-14T18:59:24Z)
• Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization [27.243322019117144]
  Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. We propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee.
  arXiv  Detail & Related papers  (2020-08-01T20:22:57Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.