4 papers
TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG
Chahana Dahal, Zuobin Xiong
Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieved documents introduce a new…
Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks
Suprim Nakarmi, Junggab Son, Yue Zhao +1
Federated Graph Neural Networks (FedGNNs) facilitate collaborative learning across multiple clients with graph-structured data while preserving user privacy. However, emerging rese…
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
An Huang, Junggab Son, Zuobin Xiong
Diffusion models have become the foundation of modern generative systems, with most research focusing primarily on improving generation efficiency and output quality. The timestep…
GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
Chahana Dahal, Ashutosh Balasubramaniam, Zuobin Xiong
Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, rai…