Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.10194 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908448887668736 |
|---|---|
| author | Klein, Tassilo Nabi, Moin |
| author_facet | Klein, Tassilo Nabi, Moin |
| contents | How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we introduce a variant of entropy - focal entropy, which mitigates the potential information leakage of the existing entropy-based approaches. We showcase feasibility on multiple benchmarks. The results suggest high target utility at moderate privacy leakage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10194 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Private Representations through Entropy-based Adversarial Training Klein, Tassilo Nabi, Moin Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we introduce a variant of entropy - focal entropy, which mitigates the potential information leakage of the existing entropy-based approaches. We showcase feasibility on multiple benchmarks. The results suggest high target utility at moderate privacy leakage. |
| title | Learning Private Representations through Entropy-based Adversarial Training |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.10194 |