# Private and Robust Contribution Evaluation in Federated Learning

arXiv: https://arxiv.org/abs/2602.21721 · HTML: https://mlsanity.com/paper/2602.21721/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Rotation Equivariant CNNs for Digital Pathology](https://mlsanity.com/paper/1806.03962/) (2018)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2110.14049/) (2021)
- [Data Banzhaf: A Robust Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2205.15466/) (2022)
- [The Shapley Value in Machine Learning](https://mlsanity.com/paper/2202.05594/) (2022)
- [GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning](https://mlsanity.com/paper/2109.02053/) (2021)
- [Collaborative Machine Learning with Incentive-Aware Model Rewards](https://mlsanity.com/paper/2010.12797/) (2020)
- [Fast-Convergent Federated Learning with Adaptive Weighting](https://mlsanity.com/paper/2012.00661/) (2020)
- [Leave-one-out Unfairness](https://mlsanity.com/paper/2107.10171/) (2021)
- [Transparent Contribution Evaluation for Secure Federated Learning on Blockchain](https://mlsanity.com/paper/2101.10572/) (2021)
- [FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2305.05506/) (2023)
- [Quality Inference in Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2007.06236/) (2020)
- [Differentially Private Shapley Values for Data Evaluation](https://mlsanity.com/paper/2206.00511/) (2022)
- [The Hidden Pitfalls of the Cosine Similarity Loss](https://mlsanity.com/paper/2406.16468/) (2024)
- [Contribution Evaluation in Federated Learning: Examining Current Approaches](https://mlsanity.com/paper/2311.09856/) (2023)
- [A Comprehensive Study of Shapley Value in Data Analytics](https://mlsanity.com/paper/2412.01460/) (2024)
- [Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning](https://mlsanity.com/paper/2506.23583/) (2025)

## Built on by (most cited first, 1 of 1)

- [Class-wise Contribution Estimation via Logit Maximization for Federated Learning](https://mlsanity.com/paper/2605.18892/) (2026)

## Abstract (arXiv)

Cross-silo federated learning allows multiple organizations to collaboratively train machine learning models without sharing raw data, but client updates can still leak sensitive information through inference attacks. Secure aggregation protects privacy by hiding individual updates, yet it complicates contribution evaluation, which is critical for fair rewards and detecting low-quality or malicious participants. Existing marginal-contribution methods, such as the Shapley value, are incompatible with secure aggregation, and practical alternatives, such as Leave-One-Out, are crude and rely on self-evaluation. We introduce two marginal-difference contribution scores compatible with secure aggregation. Fair-Private satisfies standard fairness axioms, while Everybody-Else eliminates self-evaluation and provides resistance to manipulation, addressing a largely overlooked vulnerability. We provide theoretical guarantees for fairness, privacy, robustness, and computational efficiency, and evaluate our methods on multiple medical image datasets and CIFAR10 in cross-silo settings. Our scores consistently outperform existing baselines, better approximate Shapley-induced client rankings, and improve downstream model performance as well as misbehavior detection. These results demonstrate that fairness, privacy, robustness, and practical utility can be achieved jointly in federated contribution evaluation, offering a principled solution for real-world cross-silo deployments.