Dr Hanxun Huang
Postdoctoral Research Fellow, Generative AI
School of Computing and Information Systems
18 Scholarly works
0 Projects
HIGHLIGHTS
2026
Conference Proceedings
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
DOI: 10.1145/3770855.38175832026
Journal article
A Bayesian framework for robust local intrinsic dimensionality estimation
DOI: 10.1016/j.is.2025.1026682026
Journal article
Semantic-aware Adversarial Fine-tuning for CLIP
2026
Journal article
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
DOI: 10.1109/TDSC.2025.36055972025
Conference Proceedings
T2UE: Generating Unlearnable Examples from Text Descriptions
DOI: 10.1145/3746027.37581512025
Conference Proceedings
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
DOI: 10.1109/CVPR52734.2025.028592025
Conference Proceedings
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
RECENT SCHOLARLY WORKS
2025
Conference Proceedings
Bayesian Estimation Approaches for Local Intrinsic Dimensionality
DOI: 10.1007/978-3-031-75823-2_102025
Conference Proceedings
DETECTING BACKDOOR SAMPLES IN CONTRASTIVE LANGUAGE IMAGE PRETRAINING
2024
Journal article
Imbalanced gradients: a subtle cause of overestimated adversarial robustness
DOI: 10.1007/s10994-023-06328-7