Research map / Adversarial robustness and security / Certified and empirical robustness

Adversarial Latent Feature Augmentation for Fairness

ICLR 2025 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes adversarial latent feature augmentation that targets an identified "unfair region" in the latent space to improve fairness of neural networks.

Problem

Fairness in machine learning is hard to achieve because data augmentation in input space has opaque effects on nonlinear neural networks, and existing latent-feature augmentation methods give limited insight into detecting and mitigating bias.

Approach

Introduces the concept of an "unfair region" in the latent feature space and uses adversarial augmentation of latent features to detect and mitigate bias, rather than augmenting input spaces.

Closest papers by meaning

• On the Fairness ROAD: Robust Optimization for Adversarial Debiasing (ICLR 2024 · similarity 0.90)
• Adversarial Fairness Network (AAAI 2024 · similarity 0.89)
• On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness (ICML 2025 · similarity 0.89)
• Fairness without Demographics through Shared Latent Space-Based Debiasing (AAAI 2024 · similarity 0.89)
• Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces (AAAI 2024 · similarity 0.87)
• DAFA: Distance-Aware Fair Adversarial Training (ICLR 2024 · similarity 0.87)