# Additive Adversarial Learning for Unbiased Authentication

arXiv: https://arxiv.org/abs/1905.06517 · HTML: https://mlsanity.com/paper/1905.06517/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2019.

## Built on by (most cited first, 9 of 9)

- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [FairCal: Fairness Calibration for Face Verification](https://mlsanity.com/paper/2106.03761/) (2021)
- [Adversarial Relighting Against Face Recognition](https://mlsanity.com/paper/2108.07920/) (2021)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [Score Normalization for Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2407.14087/) (2024)
- [Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge](https://mlsanity.com/paper/2407.20506/) (2024)
- [Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge](https://mlsanity.com/paper/2105.11902/) (2021)
- [AI-Assisted Authentication: State of the Art, Taxonomy and Future Roadmap](https://mlsanity.com/paper/2204.12492/) (2022)
- [Bias Mitigation in Face Recognition via Demographic-based Supervised Contrastive Learning](https://mlsanity.com/paper/2608.12971/) (2026)

## Abstract (arXiv)

Authentication is a task aiming to confirm the truth between data instances and personal identities. Typical authentication applications include face recognition, person re-identification, authentication based on mobile devices and so on. The recently-emerging data-driven authentication process may encounter undesired biases, i.e., the models are often trained in one domain (e.g., for people wearing spring outfits) while required to apply in other domains (e.g., they change the clothes to summer outfits). To address this issue, we propose a novel two-stage method that disentangles the class/identity from domain-differences, and we consider multiple types of domain-difference. In the first stage, we learn disentangled representations by a one-versus-rest disentangle learning (OVRDL) mechanism. In the second stage, we improve the disentanglement by an additive adversarial learning (AAL) mechanism. Moreover, we discuss the necessity to avoid a learning dilemma due to disentangling causally related types of domain-difference. Comprehensive evaluation results demonstrate the effectiveness and superiority of the proposed method.