Learning Private Representations through Entropy-based Adversarial Training
This work addresses privacy concerns in machine learning for users, though it appears incremental as it builds on existing entropy-based approaches.
The paper tackles the problem of learning representations that maintain predictive power while preserving user privacy by introducing focal entropy to mitigate information leakage in adversarial training. The results show high target utility with moderate privacy leakage across multiple benchmarks.
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.