Enhancing Learning with Label Differential Privacy by Vector Approximation
Zhao, Puning, Fan, Rongfei, Wu, Huiwen, Li, Qingming, Wu, Jiafei, Liu, Zhe
–arXiv.org Artificial Intelligence
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the privacy of labels by flipping them randomly, and then train a model to make the output approximate the privatized label. However, as the number of classes $K$ increases, stronger randomization is needed, thus the performances of these methods become significantly worse. In this paper, we propose a vector approximation approach, which is easy to implement and introduces little additional computational overhead. Instead of flipping each label into a single scalar, our method converts each label into a random vector with $K$ components, whose expectations reflect class conditional probabilities. Intuitively, vector approximation retains more information than scalar labels. A brief theoretical analysis shows that the performance of our method only decays slightly with $K$. Finally, we conduct experiments on both synthesized and real datasets, which validate our theoretical analysis as well as the practical performance of our method.
arXiv.org Artificial Intelligence
May-23-2024
- Country:
- Asia > China
- Zhejiang Province (0.15)
- North America > Canada
- Asia > China
- Genre:
- Research Report (0.82)
- Industry:
- Health & Medicine (0.94)
- Information Technology > Security & Privacy (1.00)