Authors

* External authors

Venue

Date

Share

Differentially Private Image Classification by Learning Priors from Random Processes

Xinyu Tang*

Ashwinee Panda*

Vikash Sehwag

Prateek Mittal*

* External authors

NeurIPS 2023

2023

Abstract

In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition.A recent focus in private learning research is improving the performance of DP-SGD on private data by incorporating priors that are learned on real-world public data.In this work, we explore how we can improve the privacy-utility tradeoff of DP-SGD by learning priors from images generated by random processes and transferring these priors to private data. We propose DP-RandP, a three-phase approach. We attain new state-of-the-art accuracy when training from scratch on CIFAR10, CIFAR100, and MedMNIST for a range of privacy budgets $\\varepsilon \\in [1, 8]$. In particular, we improve the previous best reported accuracy on CIFAR10 from $60.6 \\%$ to $72.3 \\%$ for $\\varepsilon=1$.

Related Publications

Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Model

WWW, 2025
Jie Ren, Kangrui Chen, Chen Chen, Vikash Sehwag, Yue Xing, Jiliang Tang, Lingjuan Lyu

Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their success. However, concerns have been …

Masked Differential Privacy

ECCV, 2024
Sina Sajadmanesh, Vikash Sehwag, Lingjuan Lyu, Vivek Sharma, David Schneider, Saquib Sarfraz, Rainer Stiefelhagen

Privacy-preserving computer vision is an important emerg- ing problem in machine learning and artificial intelligence. The prevalent methods tackling this problem use differential privacy or anonymization and obfuscation techniques to protect the privacy of individuals. In b…

Finding a needle in a haystack: A Black-Box Approach to Invisible Watermark Detection

ECCV, 2024
Minzhou Pan*, Zhenting Wang, Xin Dong, Vikash Sehwag, Lingjuan Lyu, Xue Lin*

In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbitrary watermarks within a given reference dataset using a clean non watermarked dataset as a ref…

  • HOME
  • Publications
  • Differentially Private Image Classification by Learning Priors from Random Processes

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.