arXiv AI July 23, 2026 By Chenyu Zhou, Yabin Peng, Wei Huang, Kunlin Li, Shuaishuai Zhang, Xinyuan Miao

FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense

arXiv:2607. 19674v1 Announce Type: cross Abstract: Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 2

Safe-FedLLM: Delving into the Safety of Federated Large Language Models

arXiv:2601. 07177v5 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs).

By Mingxiang Tao, Yu Tian, Wenxuan Tu, Yue Yang, Xue Yang, Xiangyan Tang

llms fine-tuning safety

arXiv Machine Learning

Jul 7

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs

arXiv:2605. 07961v2 Announce Type: replace Abstract: Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs).

By Hanlin Cai, Kai Li, Houtianfu Wang, Haofan Dong, Yichen Li, Falko Dressler, Ozgur B. Akan

llms agents robotics fine-tuning safety

arXiv AI

Jul 7

LLM-Enhanced Hierarchical Heterogeneous Graph Representation Learning for Malicious Python Package Detection

arXiv:2607. 03350v1 Announce Type: cross Abstract: Malicious Python packages have become a major threat to software supply chain ecosystems due to the widespread adoption of open-source repositories such as PyPI.

By Hang Gao, Xiaoyu Chen, Baoquan Cui, Zhen Tang, Peng Qiao, Fengge Wu, Jian Zhang

llms benchmarks

arXiv AI

Jun 16

Guiding Federated Graph Recommendation with LLM-encoded knowledge

arXiv:2606. 15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy.

By Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren

llms rag benchmarks safety

arXiv Machine Learning

Jun 10

Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

arXiv:2502. 01272v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks.

By Chang Liu, Hai Huang, Yujie Xing, Xingquan Zuo

rag

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

Related stories

Safe-FedLLM: Delving into the Safety of Federated Large Language Models

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs

LLM-Enhanced Hierarchical Heterogeneous Graph Representation Learning for Malicious Python Package Detection

Guiding Federated Graph Recommendation with LLM-encoded knowledge

Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

Poison to Detect: Detection of Targeted Overfitting in Federated Learning