LGCVApr 22, 2024

Ungeneralizable Examples

arXiv:2404.14016v110 citationsh-index: 66CVPR
Originality Incremental advance
AI Analysis

This addresses data privacy concerns for users sharing data online, offering a conditional approach that is incremental over existing unlearnable data methods.

The paper tackles the problem of data privacy in deep learning by introducing Ungeneralizable Examples (UGEs), which are designed to be learnable for authorized users but unlearnable for hackers, achieving reduced training performance for unauthorized networks while preserving data usability.

The training of contemporary deep learning models heavily relies on publicly available data, posing a risk of unauthorized access to online data and raising concerns about data privacy. Current approaches to creating unlearnable data involve incorporating small, specially designed noises, but these methods strictly limit data usability, overlooking its potential usage in authorized scenarios. In this paper, we extend the concept of unlearnable data to conditional data learnability and introduce \textbf{U}n\textbf{G}eneralizable \textbf{E}xamples (UGEs). UGEs exhibit learnability for authorized users while maintaining unlearnability for potential hackers. The protector defines the authorized network and optimizes UGEs to match the gradients of the original data and its ungeneralizable version, ensuring learnability. To prevent unauthorized learning, UGEs are trained by maximizing a designated distance loss in a common feature space. Additionally, to further safeguard the authorized side from potential attacks, we introduce additional undistillation optimization. Experimental results on multiple datasets and various networks demonstrate that the proposed UGEs framework preserves data usability while reducing training performance on hacker networks, even under different types of attacks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes