Hui Zhu

Enhancing Semi-Supervised Learning with Cross-Modal Knowledge

2022 · Proceedings of the 30th ACM International Conference on Multimedia

Semi-supervised learning (SSL), which leverages a small number of labeled data that rely on expert knowledge and a large number of easily accessible unlabeled data, has made rapid progress recently. However, the information comes from …

Get a Head Start: Targeted Labeling at Source with Limited Annotation Overhead for Semi-Supervised Learning

2023

Semi-supervised learning (SSL), which leverages limited labeled data and a large amount of unlabeled data for model training, has been widely studied to mitigate the requirement for expensive and time-consuming annotations. Recently proposed methods have …

Efficient and Privacy-Preserving Federated Learning Against Poisoning Adversaries

2024 · IEEE Transactions on Services Computing

The ever-growing data scale and increasingly strict privacy restraint have recently drawn extensive attention to federated learning (FL) as a multi-party machine learning paradigm for achieving high-quality model construction without data collection. Nevertheless, uploading local …

Automatic Calibration for Membership Inference Attack on Large Language Models

2025 · arXiv (Cornell University)

Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, existing methods often misinfer non-members as members, leading to …