Search papers, labs, and topics across Lattice.
This paper introduces FedLSG, a novel framework that enhances federated graph neural networks' (FedGNNs) defenses against backdoor attacks by integrating large language models (LLMs) for semantic calibration. By transforming local graph structures and client behaviors into natural language representations, FedLSG enables a more nuanced understanding of potential threats, employing a lightweight student-teacher architecture for effective evaluation and aggregation of client updates. Experimental results show that FedLSG significantly increases resilience to backdoor poisoning while maintaining the integrity of benign graph structures.
FedLSG leverages large language models to transform graph data into semantic representations, dramatically enhancing backdoor defense in federated learning.
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. To solve this, we present FedLSG, the first framework that integrates large language models (LLMs) into federated graph backdoor defense. FedLSG introduces a graph and behavior to text grounding scheme that transforms local graph structures and client update behaviors into semantically rich natural language representations. The framework further adopts a lightweight student-teacher architecture. On the server side, a full scale LLM serves as a teacher, providing global contextual guidance and evaluating client updates during aggregation to identify potentially malicious participants. On the client side, a LoRA-based student is maintained to perform semantic reasoning, to suppress the influence of edges associated with backdoor triggers. By enabling semantic interpretation of both graph patterns and client behaviors, the framework adaptively incorporates rule-based signals into message passing and client aggregation for defense. Experiments demonstrate that FedLSG significantly improves resistance to backdoor attacks without compromising graph integrity.
