47 citations · 144 across the 11 of their papers we have counts for
13 papers
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
Haoxiang Wang, Da Yu, Huishuai Zhang
Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps…
Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
Haoxiang Wang, Zinan Lin, Da Yu +1
Generating high fidelity, differentially private (DP) synthetic images offers a promising route to share and analyze sensitive visual data without compromising individual privacy.…
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni +5
Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are…
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Rachel Cummings, Damien Desfontaines, David Evans +21
In this article, we present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP), with a focus of advancing DP's depl…
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…
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…
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
Da Yu, Gautam Kamath, Janardhan Kulkarni +3
Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all d…
Availability Attacks Create Shortcuts
Da Yu, Huishuai Zhang, Wei Chen +2
Availability attacks, which poison the training data with imperceptible perturbations, can make the data \emph{not exploitable} by machine learning algorithms so as to prevent unau…
Differentially Private Fine-tuning of Language Models
Da Yu, Saurabh Naik, Arturs Backurs +9
We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus…
Large Scale Private Learning via Low-rank Reparametrization
Da Yu, Huishuai Zhang, Wei Chen +2
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing indivi…
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
Da Yu, Huishuai Zhang, Wei Chen +1
The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private…
How Does Data Augmentation Affect Privacy in Machine Learning?
Da Yu, Huishuai Zhang, Wei Chen +2
It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposi…
Stabilize Deep ResNet with A Sharp Scaling Factor
Huishuai Zhang, Da Yu, Mingyang Yi +2
We study the stability and convergence of training deep ResNets with gradient descent. Specifically, we show that the parametric branch in the residual block should be scaled down…