4 papers
Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation
Wuming Yang, Xiang Zhang, Hongmin Zhao
Heterogeneous Knowledge Distillation (HKD) aims to transfer knowledge across varying architectures (e.g., from Transformer to CNN) but inherently suffers from severe training insta…
Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems
Xinru Liu, Xianglong Zhang, Di Cai +3
Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threa…
Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference
Rongke Liu, Youwen Zhu, Lei Zhou +2
In collaborative inference (CI), transmitting intermediate representations from edge devices enables model inversion attacks (MIA) that reconstruct the original inputs , whi…
Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
Xinjian Luo, Xianglong Zhang
Federated learning (FL) is a decentralized model training framework that aims to merge isolated data islands while maintaining data privacy. However, recent studies have revealed t…