# DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence

arXiv: https://arxiv.org/abs/2509.23030 · HTML: https://mlsanity.com/paper/2509.23030/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [When Gaussian Process Meets Big Data: A Review of Scalable GPs](https://mlsanity.com/paper/1807.01065/) (2018)
- [Threats to Federated Learning: A Survey](https://mlsanity.com/paper/2003.02133/) (2020)
- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [A Survey on Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2008.10937/) (2020)
- [Unleashing the Tiger: Inference Attacks on Split Learning](https://mlsanity.com/paper/2012.02670/) (2020)
- [Communication-Efficient Edge AI: Algorithms and Systems](https://mlsanity.com/paper/2002.09668/) (2020)
- [Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy](https://mlsanity.com/paper/2106.13673/) (2021)
- [FedGH: Heterogeneous Federated Learning with Generalized Global Header](https://mlsanity.com/paper/2303.13137/) (2023)
- [Evolving Deep Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1710.10741/) (2017)
- [Dynamic ReLU](https://mlsanity.com/paper/2003.10027/) (2020)
- [From Federated Learning to Federated Neural Architecture Search: A Survey](https://mlsanity.com/paper/2009.05868/) (2020)
- [On the Convergence and Calibration of Deep Learning with Differential Privacy](https://mlsanity.com/paper/2106.07830/) (2021)
- [Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets](https://mlsanity.com/paper/2003.13549/) (2020)
- [FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks](https://mlsanity.com/paper/2210.14226/) (2022)
- [Real-time Federated Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2003.02793/) (2020)
- [SPIDER: Searching Personalized Neural Architecture for Federated Learning](https://mlsanity.com/paper/2112.13939/) (2021)
- [Comparison of Methods Generalizing Max- and Average-Pooling](https://mlsanity.com/paper/2103.01746/) (2021)
- [A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search](https://mlsanity.com/paper/2204.03916/) (2022)

## Abstract (arXiv)

The Sixth-Generation (6G) network envisions pervasive artificial intelligence (AI) as a core goal, enabled by edge intelligence through on-device data utilization. To realize this vision, federated learning (FL) has emerged as a key paradigm for collaborative training across edge devices. However, the sensitivity and heterogeneity of edge data pose key challenges to FL: parameter sharing risks data reconstruction, and a unified global model struggles to adapt to diverse local distributions. In this paper, we propose a novel federated learning framework that integrates personalized differential privacy (DP) and adaptive model design. To protect training data, we leverage sample-level representations for knowledge sharing and apply a personalized DP strategy to resist reconstruction attacks. To ensure distribution-aware adaptation under privacy constraints, we develop a privacy-aware neural architecture search (NAS) algorithm that generates locally customized architectures and hyperparameters. To the best of our knowledge, this is the first personalized DP solution tailored for representation-based FL with theoretical convergence guarantees. Our scheme achieves strong privacy guarantees for training data while significantly outperforming state-of-the-art methods in model performance. Experiments on benchmark datasets such as CIFAR-10 and CIFAR-100 demonstrate that our scheme improves accuracy by 6.82% over the federated NAS method PerFedRLNAS, while reducing model size to 1/10 and communication cost to 1/20.