{"ID":2894834,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10194","arxiv_id":"2507.10194","title":"Learning Private Representations through Entropy-based Adversarial Training","abstract":"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.","short_abstract":"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 informatio...","url_abs":"https://arxiv.org/abs/2507.10194","url_pdf":"https://arxiv.org/pdf/2507.10194v1","authors":"[\"Tassilo Klein\",\"Moin Nabi\"]","published":"2025-07-14T12:01:08Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false}