# Robust Federated Inference

arXiv: https://arxiv.org/abs/2510.00310 · HTML: https://mlsanity.com/paper/2510.00310/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [One-Shot Federated Learning](https://mlsanity.com/paper/1902.11175/) (2019)
- [FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings](https://mlsanity.com/paper/2210.04620/) (2022)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [Byzantine Stochastic Gradient Descent](https://mlsanity.com/paper/1803.08917/) (2018)
- [Practical One-Shot Federated Learning for Cross-Silo Setting](https://mlsanity.com/paper/2010.01017/) (2020)
- [Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity](https://mlsanity.com/paper/2302.01772/) (2023)
- [Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums](https://mlsanity.com/paper/2205.12173/) (2022)
- [Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation](https://mlsanity.com/paper/1911.09272/) (2019)
- [Fusing Models with Complementary Expertise](https://mlsanity.com/paper/2310.01542/) (2023)
- [Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation](https://mlsanity.com/paper/2209.04599/) (2022)
- [LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity](https://mlsanity.com/paper/2410.03953/) (2024)
- [FLCert: Provably Secure Federated Learning against Poisoning Attacks](https://mlsanity.com/paper/2210.00584/) (2022)
- [Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting](https://mlsanity.com/paper/2402.15070/) (2024)
- [Revisiting Ensembling in One-Shot Federated Learning](https://mlsanity.com/paper/2411.07182/) (2024)
- [Decentralized Low-Latency Collaborative Inference via Ensembles on the Edge](https://mlsanity.com/paper/2206.03165/) (2022)
- [Collaborative Learning via Prediction Consensus](https://mlsanity.com/paper/2305.18497/) (2023)
- [Byzantine Spectral Ranking](https://mlsanity.com/paper/2211.07902/) (2022)
- [Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers](https://mlsanity.com/paper/2402.02951/) (2024)

## Built on by (most cited first, 2 of 2)

- [Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving](https://mlsanity.com/paper/2603.02214/) (2026)
- [Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration](https://mlsanity.com/paper/2609.07230/) (2026)

## Abstract (arXiv)

Federated inference, in the form of one-shot federated learning, edge ensembles, or federated ensembles, has emerged as an attractive solution to combine predictions from multiple models. This paradigm enables each model to remain local and proprietary while a central server queries them and aggregates predictions. Yet, the robustness of federated inference has been largely neglected, leaving them vulnerable to even simple attacks. To address this critical gap, we formalize the problem of robust federated inference and provide the first robustness analysis of this class of methods. Our analysis of averaging-based aggregators shows that the error of the aggregator is small either when the dissimilarity between honest responses is small or the margin between the two most probable classes is large. Moving beyond linear averaging, we show that problem of robust federated inference with non-linear aggregators can be cast as an adversarial machine learning problem. We then introduce an advanced technique using the DeepSet aggregation model, proposing a novel composition of adversarial training and test-time robust aggregation to robustify non-linear aggregators. Our composition yields significant improvements, surpassing existing robust aggregation methods by 4.7 - 22.2% in accuracy points across diverse benchmarks.