paper-with-me

Papers

TMI! Finetuned Models Leak Private Information from their Pretraining Data

2023-06-01 · John Abascal, Stanley Wu, Alina Oprea, Jonathan Ullman

Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm has been especially popular for $\textit{privacy}$ in machine learning, where the pretrained model is considered public, and only the data for finetuning is considered sensitive. However, there are reasons to believe that the data used for pretraining is still sensitive, making it essential to understand how much information the finetuned model leaks about the pretraining data. In this work we propose a new membership-inference threat model where the adversary only has access to the finetuned model and would like to infer the membership of the pretraining data. To realize this threat model, we implement a novel metaclassifier-based attack, $\textbf{TMI}$, that leverages the influence of memorized pretraining samples on predictions in the downstream task. We evaluate $\textbf{TMI}$ on both vision and natural language tasks across multiple transfer learning settings, including finetuning with differential privacy. Through our evaluation, we find that $\textbf{TMI}$ can successfully infer membership of pretraining examples using query access to the finetuned model. An open-source implementation of $\textbf{TMI}$ can be found on GitHub: https://github.com/johnmath/tmi-pets24.

📄 PDF Abstract BibTeX arXiv:2306.01181

Code (1)

johnmath/tmi-pets24 공식 구현 pytorch

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Quantifying and Localizing Usable Information Leakage from Neural Network Gradients

2021-05-28 · Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Soteris Demetriou 외

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract …

Attribute

ContextLeak: Auditing Leakage in Private In-Context Learning Methods

2025-12-18 · Jacob Choi, Shuying Cao, Xingjian Dong, Amin Banayeeanzade 외 arxiv

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensi…

The Trade-Offs of Private Prediction

2020-07-09 · Laurens van der Maaten, Awni Hannun

Machine learning models leak information about their training data every time they reveal a prediction. This is problematic when the training data needs to remain private. Private prediction methods limit how much inform…

Prediction

Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage

2022-03-29 · CVPR 2022 1 · Zhuohang Li, Jiaxin Zhang, Luyang Liu, Jian Liu

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their…

Bayesian OptimizationFederated Learning

Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information

2022-09-21 · Kiwan Maeng, Chuan Guo, Sanjay Kariyappa, Edward Suh

Split learning and inference propose to run training/inference of a large model that is split across client devices and the cloud. However, such a model splitting imposes privacy concerns, because the activation flowing …