activity
20162026
most citedDifferentially Private Fine-tuning of Language Models

47 citations · 214 across the 48 of their papers we have counts for

collaborators
Showing 2022Show all

8 papers · 1 filter

cs.LG2022★ 4 cited

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

Jiyan He, Xuechen Li, Da Yu +6

Differentially private deep learning has recently witnessed advances in computational efficiency and privacy-utility trade-off. We explore whether further improvements along the tw…

cs.CR2022

Similarity Distribution based Membership Inference Attack on Person Re-identification

Junyao Gao, Xinyang Jiang, Huishuai Zhang +6

While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training dat…

cs.CV2022★ 5 cited

Denoising Masked AutoEncoders Help Robust Classification

Quanlin Wu, Hang Ye, Yuntian Gu +3

In this paper, we propose a new self-supervised method, which is called Denoising Masked AutoEncoders (DMAE), for learning certified robust classifiers of images. In DMAE, we corru…

cs.LG2022★ 3 cited

Provable Adaptivity of Adam under Non-uniform Smoothness

Bohan Wang, Yushun Zhang, Huishuai Zhang +6

Adam is widely adopted in practical applications due to its fast convergence. However, its theoretical analysis is still far from satisfactory. Existing convergence analyses for Ad…

cs.LG2022★ 8 cited

Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization

Xiaodong Yang, Huishuai Zhang, Wei Chen +1

By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data. In this paper, we study two al…

cs.LG2022

Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks

Huishuai Zhang, Da Yu, Yiping Lu +1

Adversarial examples, which are usually generated for specific inputs with a specific model, are ubiquitous for neural networks. In this paper we unveil a surprising property of ad…