paper-with-me

홈 › Papers

Private and Stable Test-Time Adaptation with Differential Privacy

2026-06-01 · Zefeng Li, Qiaoyue Tang, Mathias Lecuyer, Evan Shelhamer arxiv

Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs. To control this privacy risk, we cast multiple popular TTA methods (Tent, EATA, SAR, DeYO, and COME) into differential privacy (DP) forms that apply per-sample gradient clipping and Gaussian noise for all updates. On ImageNet-C, our DP-TTA methods provide adequate privacy at small cost to accuracy, and in the low-privacy regime the clipping mechanism of DP can even improve the accuracy and stability of adaptation in the continual setting. These improvements to privacy and accuracy come at only modest computational overhead. These first results on private TTA raise awareness of the issue, inform the development of more private test-time updates, and identify per-sample clipping as an effective technique for improving the accuracy and stability of adaptation.

📄 PDF Abstract BibTeX arXiv:2606.01908

Code (0)

등록된 구현이 없습니다.

Tasks

Test-time Adaptation

Similar Papers 제목 키워드 기반

Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings

2024-11-22 · Pura Peetathawatchai, Wei-Ning Chen, Berivan Isik, Sanmi Koyejo 외

We introduce a novel method for adapting diffusion models under differential privacy (DP) constraints, enabling privacy-preserving style and content transfer without fine-tuning model weights. Traditional approaches to p…

Privacy PreservingStyle Transfer

Connecting Robust Shuffle Privacy and Pan-Privacy

2020-04-20 · Victor Balcer, Albert Cheu, Matthew Joseph, Jieming Mao

In the \emph{shuffle model} of differential privacy, data-holding users send randomized messages to a secure shuffler, the shuffler permutes the messages, and the resulting collection of messages must be differentially p…

Pan-Private Uniformity Testing

2019-11-04 · Kareem Amin, Matthew Joseph, Jieming Mao

A centrally differentially private algorithm maps raw data to differentially private outputs. In contrast, a locally differentially private algorithm may only access data through public interaction with data holders, and…

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares

2024-04-23 · Gavin Brown, Jonathan Hayase, Samuel Hopkins, Weihao Kong 외

We present a sample- and time-efficient differentially private algorithm for ordinary least squares, with error that depends linearly on the dimension and is independent of the condition number of $X^\top X$, where $X$ i…

Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent

2020-06-25 · Lauren Watson, Benedek Rozemberczki, Rik Sarkar

Private machine learning involves addition of noise while training, resulting in lower accuracy. Intuitively, greater stability can imply greater privacy and improve this privacy-utility tradeoff. We study this role of s…

feature selection