摘要
This paper investigates the privacy⁃utility trade⁃off of local label differential privacy(L⁃LDP) in deep learning tasks such as image classification. Theoretical analysis reveals that the privacy enhancement of L⁃LDP in⁃ creases linearly with the privacy budget, while model utility degrades in an inverse⁃proportional manner; this intrin⁃ sic imbalance makes it difficult for L⁃LDP to maintain a stable trade⁃off across different privacy levels. To address this limitation, an improved L⁃LDP algorithm based on feature perturbation and structured resampling is proposed. The proposed method preserves the original privacy guarantees of L⁃LDP while enhancing data diversity and model robustness through feature⁃space clustering and randomized resampling. Experimental results demonstrate that the proposed algorithm significantly improves privacy protection without sacrificing model utility, achieving a more fa⁃ vorable balance between privacy and performance across multiple image classification tasks.
| 投稿的翻译标题 | A feature⁃perturbed local label differential privacy algorithm |
|---|---|
| 源语言 | 繁体中文 |
| 页(从-至) | 819-827 |
| 页数 | 9 |
| 期刊 | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University |
| 卷 | 44 |
| 期 | 4 |
| DOI | |
| 出版状态 | 已出版 - 8月 2026 |
| 已对外发布 | 是 |
关键词
- deep learning
- differential privacy
- feature perturbation
- structured resampling
学术指纹
探究 '基于特征扰动的本地差分隐私算法' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver