Masked Differential Privacy

• Main Authors: Schneider, David, Sajadmanesh, Sina, Sehwag, Vikash, Sarfraz, Saquib, Stiefelhagen, Rainer, Lyu, Lingjuan, Sharma, Vivek
• Format: Journal Article
• Language: English
• Published: 22-10-2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2410.17098

Proceedings of the 2nd International Workshop on
Privacy-Preserving Computer Vision, ECCV 2024 Privacy-preserving computer vision is an important emerging problem in
machine learning and artificial intelligence. The prevalent methods tackling
this problem use differential privacy or anonymization and obfuscation
techniques to protect the privacy of individuals. In both cases, the utility of
the trained model is sacrificed heavily in this process. In this work, we
propose an effective approach called masked differential privacy (MaskDP),
which allows for controlling sensitive regions where differential privacy is
applied, in contrast to applying DP on the entire input. Our method operates
selectively on the data and allows for defining non-sensitive spatio-temporal
regions without DP application or combining differential privacy with other
privacy techniques within data samples. Experiments on four challenging action
recognition datasets demonstrate that our proposed techniques result in better
utility-privacy trade-offs compared to standard differentially private training
in the especially demanding $\epsilon<1$ regime.