Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design
Not on the map. Why?
Abstract (arXiv)
The proliferation of IoT devices has fueled distributed edge systems to collect vast amounts of sensitive data, creating fertile ground for on-device machine learning applications. While federated learning (FL) mitigates privacy concerns by exchanging model parameters instead of raw data, we identify a critical blind spot in current research. We examine the most commonly used personalized federated learning (PFL) methods, which allow clients to maintain private, personalized models to address data heterogeneity across clients. Through systematic analysis, we reveal that PFL methods exhibit heightened vulnerability to transfer-based adversarial attacks compared to centralized learning paradigms. Wherein, malicious clients can exploit local model knowledge to craft adversarial examples that can compromise peer clients' personalized models. We establish this vulnerability through both theoretical analysis and empirical evaluation across multiple benchmark datasets, demonstrating significant accuracy drops across various PFL methods. To address this challenge, we propose a defense framework combining stochastic input noise, input-scaled trace regularization, and parameter sensitivity maximization to improve FL's robustness. Our findings establish the first systematic study of adversarial threats in PFL systems, providing both diagnostic tools and practical countermeasures.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 22 Jun 2026.
Builds on
25 of 39 references.
References · 25
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2021Convex optimizationcited by 2,515
- 2016Adversarial examples in the physical worldcited by 1,769
- 2019Deep Leakage from Gradientscited by 1,021
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
- 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
- 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
13 more
- 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
- 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
- 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
- 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 167
- 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
- 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
- 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 70
- 2019Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothingcited by 54
- 2023Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaborationcited by 23
- 2024ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issuescited by 10
- 2023Adversarial Attack Based on Prediction-Correctioncited by 7
- 2022Enhance transferability of adversarial examples with model architecturecited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.