5 citations · 10 across the 11 of their papers we have counts for
11 papers
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…
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…
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…
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…
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…
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…
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…
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…
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…