arXiv Machine Learning August 27, 2026 By Zuobin Xiong, Deval Mukherjee, Homook Cho, Wei Li

Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning

Read the original on arXiv Machine Learning →

The paper investigates how adversarial examples transfer between client models in federated learning and explores the relationship between these examples and client data distributions. It proposes a defense strategy based on adversarial training that leverages the transferability of model robustness. Experiments on real-life datasets demonstrate that the new attack and defense methods outperform existing state‑of‑the‑art approaches.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Aug 25

Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning

The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a...

benchmarks safety

arXiv Machine Learning

Aug 24

BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

arXiv:2608.21137v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model...

By Mouhamed Amine Bouchiha, Gregory Blanc, Yufei Han

benchmarks

arXiv Machine Learning

Aug 21

Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability

arXiv:2509. 23689v2 Announce Type: replace Abstract: Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into one model that retains performance across different tasks.

By Mauro Conti, Ankit Gangwal, Aaryan Ajay Sharma

fine-tuning safety

arXiv AI

Aug 10

Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning

arXiv:2608. 06637v1 Announce Type: cross Abstract: Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior.

By Srinivasan Subramanian, Md. Abdullah Al Hafiz Khan, Kazi Aminul Islam

benchmarks safety

arXiv Machine Learning

Aug 4

FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices

arXiv:2608. 01095v1 Announce Type: new Abstract: Federated learning (FL) enables multiple intelligent devices to collaboratively train a high-accuracy model without sharing raw data.

By Hongliang Zhang, Zhongyuan Yu, Fenghua Xu, Teng Hu, Jian Meng, Jiguo Yu

arXiv AI

Jul 20

Poison to Detect: Detection of Targeted Overfitting in Federated Learning

arXiv:2509. 11974v2 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training among clients without centralising data, making it a widely adopted privacy-enhancing technology (PET).

By Soumia Zohra El Mestari, Maciej Krzysztof Zuziak, Gabriele Lenzini

safety

One email a morning, machine-written

Related stories

Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning

BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability

Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning

FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices

Poison to Detect: Detection of Targeted Overfitting in Federated Learning