IPProtect: protecting the intellectual property of visual datasets during data valuation
Data trading is essential to accelerate the development of data-driven machine learning pipelines. The central problem in data trading is to estimate the utility of a seller's dataset with respect to a given buyer's machine learning task, also known as data valuation. Typically, data valuation requires one or more participants to share their raw dataset with others, leading to potential risks of intellectual property (IP) violations. In this paper, we tackle the novel task of preemptively protecting the IP of datasets that need to be shared during data valuation. First, we identify and formalize two kinds of novel IP risks in visual datasets: data-item (image) IP and statistical (dataset) IP. Then, we propose a novel algorithm to convert the raw dataset into a sanitized version, that provides resistance to IP violations, while at the same time allowing accurate data valuation. The key idea is to limit the transfer of information from the raw dataset to the sanitized dataset, thereby protecting against potential intellectual property violations. Next, we analyze our method for the likely existence of a solution and immunity against reconstruction attacks. Finally, we conduct extensive experiments on three computer vision datasets demonstrating the advantages of our method in comparison to other baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Data ValuationSimilar Papers 제목 키워드 기반
AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields
As Neural Radiance Fields (NeRFs) have emerged as a powerful tool for 3D scene representation and novel view synthesis, protecting their intellectual property (IP) from unauthorized use is becoming increasingly crucial. …
Novel View SynthesisImage ClassificationPragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments, adversaries can copy and reuse these pr…
FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
Federated learning (FL) enables multiple clients to collaboratively train a shared global model while preserving the privacy of their local data. Within this paradigm, the intellectual property rights (IPR) of client mod…
Contrastive LearningFederated LearningModel Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection
As scientific and technological advancements result from human intellectual labor and computational costs, protecting model intellectual property (IP) has become increasingly important to encourage model creators and own…
modelIPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary
A deep neural network (DNN) classifier represents a model owner's intellectual property as training a DNN classifier often requires lots of resource. Watermarking was recently proposed to protect the intellectual propert…
General Classification