Human-Centered Machine Learning (HCML) models often face challenges due to inherent biases related to population variability and limited access to large datasets. This results in algorithms that fail to generalize and accommodate out-of-distribution samples, thereby hindering real-world applications. Additionally, standard training procedures tend to make neural networks vulnerable to privacy risks such as reconstruction attacks. To address these issues, we propose a novel training method based on an adversarial network that aims to reduce the representation bias induced by the lack of diversity among training samples. Unlike similar approaches that use a known bias predictor as the adversarial signal, our method mitigates multiple unknown biases, acting as an effective regularization term that reduces the validation gap while also removing non-essential features. This feature selection further improves privacy by preventing the model from being repurposed or used to retrieve information about training or inferred samples, as demonstrated on the IMDb-Face dataset where the method achieves approximately a 6.7% improvement in accuracy and enhances robustness against reconstruction attacks by about 174%.