GRMP crafts malicious updates via variational graph autoencoders on overheard benign feature graphs, degrading global LLM accuracy in federated IoA while evading statistical detection.
Large model based agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Graph representation learning plus iterative augmented Lagrangian optimization creates stronger, harder-to-detect model manipulation attacks on federated LLM fine-tuning, cutting global accuracy by up to 26%.
citing papers explorer
-
Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents
GRMP crafts malicious updates via variational graph autoencoders on overheard benign feature graphs, degrading global LLM accuracy in federated IoA while evading statistical detection.
-
Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
Graph representation learning plus iterative augmented Lagrangian optimization creates stronger, harder-to-detect model manipulation attacks on federated LLM fine-tuning, cutting global accuracy by up to 26%.