Publications (32)
Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network
Yan Pang, Chao Liu
Dynamic graph neural networks have been widely used in modeling and representation learning of graph structure data. Current dynamic representation learning focuses on either discr…
White-box Membership Inference Attacks against Diffusion Models
Yan Pang, Tianhao Wang, Xuhui Kang +2
Diffusion models have begun to overshadow GANs and other generative models in industrial applications due to their superior image generation performance. The complex architecture o…
Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs
Fengzhu Zeng, Wenqian Li, Wei Gao +1
Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training dete…
Data Valuation and Selection in a Federated Model Marketplace
Wenqian Li, Youjia Yang, Ruoxi Jia +1
In the era of Artificial Intelligence (AI), marketplaces have become essential platforms for facilitating the exchange of data products to foster data sharing. Model transactions p…
Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
Yan Pang, Wenlong Meng, Xiaojing Liao +1
With the rapid development of large language models, the potential threat of their malicious use, particularly in generating phishing content, is becoming increasingly prevalent. L…
Enhanced boiling heat transfer using conducting-insulating microcavity surfaces in an electric field: A lattice Boltzmann study
Fanming Cai, Zhaomiao Liu, Nan Zheng +1
The field trap effect on the microcavity surface under the action of an electric field is not conducive to boiling heat transfer. This numerical study found that using conducting-i…
PrivMVMF: Privacy-Preserving Multi-View Matrix Factorization for Recommender Systems
Peihua Mai, Yan Pang
With an increasing focus on data privacy, there have been pilot studies on recommender systems in a federated learning (FL) framework, where multiple parties collaboratively train…
Private Wasserstein Distance
Wenqian Li, Yan Pang
Wasserstein distance is a key metric for quantifying data divergence from a distributional perspective. However, its application in privacy-sensitive environments, where direct sha…
Generation of vector beams in planar photonic crystal cavities with multiple missing-hole defects
Chenyang Zhao, Xuetao Gan, Sheng Liu +2
We propose a novel method to generate vector beams in planar photonic crystal cavities with multiple missing-hole defects. Simulating the resonant modes in the cavities, we observe…
Vertical Federated Graph Neural Network for Recommender System
Peihua Mai, Yan Pang
Conventional recommender systems are required to train the recommendation model using a centralized database. However, due to data privacy concerns, this is often impractical when…
MCM: Mamba-based Cardiac Motion Tracking using Sequential Images in MRI
Jiahui Yin, Xinxing Cheng, Jinming Duan +4
Myocardial motion tracking is important for assessing cardiac function and diagnosing cardiovascular diseases, for which cine cardiac magnetic resonance (CMR) has been established…
Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification
Yan Pang, Chao Liu
Graph neural networks can be effectively applied to find solutions for many real-world problems across widely diverse fields. The success of graph neural networks is linked to the…
Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
Jingqi Zhang, Ruibo Chen, Yingqing Yang +3
Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrig…
Towards Understanding Unsafe Video Generation
Yan Pang, Aiping Xiong, Yang Zhang +1
Video generation models (VGMs) have demonstrated the capability to synthesize high-quality output. It is important to understand their potential to produce unsafe content, such as…
Split-and-Denoise: Protect large language model inference with local differential privacy
Peihua Mai, Ran Yan, Zhe Huang +2
Large Language Models (LLMs) excel in natural language understanding by capturing hidden semantics in vector space. This process enriches the value of text embeddings for various d…
Closed-form Solutions: A New Perspective on Solving Differential Equations
Shu Wei, Yanjie Li, Lina Yu +8
The quest for analytical solutions to differential equations has traditionally been constrained by the need for extensive mathematical expertise. Machine learning methods like gene…
GFlowCausal: Generative Flow Networks for Causal Discovery
Wenqian Li, Yinchuan Li, Shengyu Zhu +3
Causal discovery aims to uncover causal structure among a set of variables. Score-based approaches mainly focus on searching for the best Directed Acyclic Graph (DAG) based on a pr…
Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
Yan Pang, Tianhao Wang
With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-qu…
VGMShield: Mitigating Misuse of Video Generative Models
Yan Pang, Baicheng Chen, Yang Zhang +1
With the rapid advancement in video generation, people can conveniently use video generation models to create videos tailored to their specific desires. As a result, there are also…
ConfusionPrompt: Practical Private Inference for Online Large Language Models
Peihua Mai, Youjia Yang, Ran Yan +2
State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant priv…
SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
Peihua Mai, Youlong Ding, Ziyan Lyu +2
Federated recommender system (FedRec) has emerged as a solution to protect user data through collaborative training techniques. A typical FedRec involves transmitting the full mode…
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Peihua Mai, Ran Yan, Yan Pang
Federated learning (FL) allows multiple devices to train a model collaboratively without sharing their data. Despite its benefits, FL is vulnerable to privacy leakage and poisoning…
Data Valuation and Detections in Federated Learning
Wenqian Li, Shuran Fu, Fengrui Zhang +1
Federated Learning (FL) enables collaborative model training while preserving the privacy of raw data. A challenge in this framework is the fair and efficient valuation of data, wh…
When Sample Selection Bias Precipitates Model Collapse
Xinbao Qiao, Xianglong Du, Wei Liu +4
The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated training erodes distributional tails and homogenizes…
Infinitely many solutions for three quasilinear Laplacian systems on weighted graphs
Yan Pang, Junping Xie, Xingyong Zhang
We investigate a generalized poly-Laplacian system with a parameter on weighted finite graph, a generalized poly-Laplacian system with a parameter and Dirichlet boundary value on w…
Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition
Xiaocong Zeng, Craig Michoski, Yan Pang +1
In this work, we address the often-overlooked issue of Timescale Dependent Label Inconsistency (TsDLI) in training neural network models for EEG-based human emotion recognition. To…
As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Files
Haodong Li, Jingqi Zhang, Xiao Cheng +3
The remarkable language ability of Large Language Models (LLMs) stems from extensive training on vast datasets, often including copyrighted material, which raises serious concerns…
Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
Weihang Wang, Xinhao Li, Ziyue Wang +5
Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual infor…
Existence of three solutions for a poly-Laplacian system on graphs
Yan Pang, Xingyong Zhang
We deal with the existence of three distinct solutions for a poly-Laplacian system with a parameter on finite graphs and a -Laplacian system with a parameter on locally fini…
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
Peihua Mai, Xuanrong Gao, Youlong Ding +3
With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-pr…
MRMMIA: Membership Inference Attacks on Memory in Chat Agents
Kai Chen, Yan Pang, Tianhao Wang
Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine lear…
DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks
Wenqian Li, Yinchuan Li, Zhigang Li +2
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over the years. Existing literature mainly focus on selecting a subgraph,…