用焦点熵对抗训练，让模型学有用表示同时保护隐私。
Learning Private Representations through Entropy-based Adversarial Training
- 引入焦点熵替代传统熵，减少敏感信息泄露。
- 在多个基准上实现高目标任务性能与可控隐私泄露。
- 适合需要隐私保护的表征学习场景。
如何在保持高预测能力的同时保护用户隐私？我们提出一种对抗式表征学习方法，用于从学习到的表征中净化敏感内容。具体地，引入一种新型熵——焦点熵，缓解现有基于熵方法潜在的信息泄露问题。我们在多个基准上验证了该方法的有效性，结果表明可在中等隐私泄露水平下实现较高的目标任务性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。