Hanxun Huang

41 papers A* 9B 2Journal 29
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Bayesian framework for robust local intrinsic dimensionality estimation.
Inf. Syst.
Zaher Joukhadar, Hanxun Huang, Sarah Monazam Erfani, Ricardo J. G. B. Campello, Michael E. Houle, James Bailey
2026 J jnl
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs.
CoRR
Yige Li, Wei Zhao, Zhe Li, Nay Myat Min, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Yu-Gang Jiang, Jun Sun
2026 J jnl
Internal Safety Collapse in Frontier Large Language Models.
CoRR
Yutao Wu, Xiao Liu, Yifeng Gao, Xiang Zheng, Hanxun Huang, Yige Li, Cong Wang, Bo Li, Xingjun Ma, Yu-Gang Jiang
2026 J jnl
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs.
CoRR
Xiang Zheng, Yutao Wu, Hanxun Huang, Yige Li, Xingjun Ma, Bo Li, Yu-Gang Jiang, Cong Wang
2026 J jnl
Semantic-aware Adversarial Fine-tuning for CLIP.
CoRR
Jiacheng Zhang, Jinhao Li, Hanxun Huang, Sarah M. Erfani, Benjamin I. P. Rubinstein, Feng Liu
2026 J jnl
Semantic-aware Adversarial Fine-tuning for CLIP.
Trans. Mach. Learn. Res.
Jiacheng Zhang, Jinhao Li, Hanxun Huang, Sarah Monazam Erfani, Benjamin I. P. Rubinstein, Feng Liu
2026 J jnl
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks.
IEEE Trans. Dependable Secur. Comput.
Yige Li, Jiabo He, Hanxun Huang, Jun Sun, Xingjun Ma, Yu-Gang Jiang
2026 J jnl
Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models.
CoRR
Kaiyuan Cui, Yige Li, Yutao Wu, Xingjun Ma, Sarah M. Erfani, Christopher Leckie, Hanxun Huang
2025 J jnl
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds.
CoRR
Qizhou Wang, Hanxun Huang, Guansong Pang, Sarah M. Erfani, Christopher Leckie
2025 J jnl
AutoBackdoor: Automating Backdoor Attacks via LLM Agents.
CoRR
Yige Li, Zhe Li, Wei Zhao, Nay Myat Min, Hanxun Huang, Xingjun Ma, Jun Sun
2025 J jnl
BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models.
CoRR
Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen, Xin Wang, Yixu Wang, Xingjun Ma, Yu-Gang Jiang
2025 J jnl
CURVALID: Geometrically-guided Adversarial Prompt Detection.
CoRR
Canaan Yung, Hanxun Huang, Sarah Monazam Erfani, Christopher Leckie
2025 A* conf
Detecting Backdoor Samples in Contrastive Language Image Pretraining.
ICLR
Hanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, James Bailey
2025 J jnl
Detecting Backdoor Samples in Contrastive Language Image Pretraining.
CoRR
Hanxun Huang, Sarah M. Erfani, Yige Li, Xingjun Ma, James Bailey
2025 J jnl
Safety at Scale: A Comprehensive Survey of Large Model Safety.
CoRR
Xingjun Ma, Yifeng Gao, Yixu Wang, Ruofan Wang, Xin Wang, Ye Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhan Zhao, Hanxun Huang, Yige Li, Jiaming Zhang, Xiang Zheng, Yang Bai, Zuxuan Wu, Xipeng Qiu, Jingfeng Zhang, Yiming Li, Jun Sun, Cong Wang, Jindong Gu, Baoyuan Wu, Siheng Chen, Tianwei Zhang, Yang Liu, Mingming Gong, Tongliang Liu, Shirui Pan, Cihang Xie, Tianyu Pang, Yinpeng Dong, Ruoxi Jia, Yang Zhang, Shiqing Ma, Xiangyu Zhang, Neil Gong, Chaowei Xiao, Sarah M. Erfani, Bo Li, Masashi Sugiyama, Dacheng Tao, James Bailey, Yu-Gang Jiang
2025 J jnl
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.
Found. Trends Priv. Secur.
Xingjun Ma, Yifeng Gao, Yixu Wang, Ruofan Wang, Xin Wang, Ye Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhao Zhao, Hanxun Huang, Yige Li, Yutao Wu, Jiaming Zhang, Xiang Zheng, Yang Bai, Yiming Li, Zuxuan Wu, Xipeng Qiu, Jingfeng Zhang, Xudong Han, Haonan Li, Jun Sun, Cong Wang, Jindong Gu, Baoyuan Wu, Siheng Chen, Tianwei Zhang, Yang Liu, Mingming Gong, Tongliang Liu, Shirui Pan, Cihang Xie, Tianyu Pang, Yinpeng Dong, Ruoxi Jia, Yang Zhang, Shiqing Ma, Xiangyu Zhang, Neil Gong, Chaowei Xiao, Sarah M. Erfani, Tim Baldwin, Bo Li, Masashi Sugiyama, Dacheng Tao, James Bailey, Yu-Gang Jiang
2025 A* conf
T2UE: Generating Unlearnable Examples from Text Descriptions.
ACM Multimedia
Xingjun Ma, Hanxun Huang, Tianwei Song, Ye Sun, Yifeng Gao, Yu-Gang Jiang
2025 J jnl
T2UE: Generating Unlearnable Examples from Text Descriptions.
CoRR
Xingjun Ma, Hanxun Huang, Tianwei Song, Ye Sun, Yifeng Gao, Yu-Gang Jiang
2025 A* conf
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks.
CVPR
Yong Xie, Weijie Zheng, Hanxun Huang, Guangnan Ye, Xingjun Ma
2025 A* conf
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP.
ICML
Hanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, James Bailey
2025 J jnl
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP.
CoRR
Hanxun Huang, Sarah M. Erfani, Yige Li, Xingjun Ma, James Bailey
2024 J jnl
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models.
CoRR
Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun
2024 B conf
Bayesian Estimation Approaches for Local Intrinsic Dimensionality.
SISAP
Zaher Joukhadar, Hanxun Huang, Sarah Monazam Erfani, Ricardo J. G. B. Campello, Michael E. Houle, James Bailey
2024 J jnl
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers.
CoRR
Weijie Zheng, Xingjun Ma, Hanxun Huang, Zuxuan Wu, Yu-Gang Jiang
2024 J jnl
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models.
CoRR
Yige Li, Hanxun Huang, Jiaming Zhang, Xingjun Ma, Yu-Gang Jiang
2024 J jnl
Imbalanced gradients: a subtle cause of overestimated adversarial robustness.
Mach. Learn.
Xingjun Ma, Linxi Jiang, Hanxun Huang, Zejia Weng, James Bailey, Yu-Gang Jiang
2024 A* conf
LDReg: Local Dimensionality Regularized Self-Supervised Learning.
ICLR
Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani, Xingjun Ma, Michael E. Houle, James Bailey
2024 J jnl
LDReg: Local Dimensionality Regularized Self-Supervised Learning.
CoRR
Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani, Xingjun Ma, Michael E. Houle, James Bailey
2024 J jnl
Multi-Trigger Backdoor Attacks: More Triggers, More Threats.
CoRR
Yige Li, Xingjun Ma, Jiabo He, Hanxun Huang, Yu-Gang Jiang
2024 — —
Robust and Trustworthy Machine Learning.
Hanxun Huang
2024 J jnl
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks.
CoRR
Yong Xie, Weijie Zheng, Hanxun Huang, Guangnan Ye, Xingjun Ma
2023 A* conf
Distilling Cognitive Backdoor Patterns within an Image.
ICLR
Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey
2023 J jnl
Distilling Cognitive Backdoor Patterns within an Image.
CoRR
Hanxun Huang, Xingjun Ma, Sarah M. Erfani, James Bailey
2021 A* conf
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks.
NeurIPS
Hanxun Huang, Yisen Wang, Sarah M. Erfani, Quanquan Gu, James Bailey, Xingjun Ma
2021 J jnl
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks.
CoRR
Hanxun Huang, Yisen Wang, Sarah Monazam Erfani, Quanquan Gu, James Bailey, Xingjun Ma
2021 B conf
Neural Architecture Search via Combinatorial Multi-Armed Bandit.
IJCNN
Hanxun Huang, Xingjun Ma, Sarah M. Erfani, James Bailey
2021 J jnl
Neural Architecture Search via Combinatorial Multi-Armed Bandit.
CoRR
Hanxun Huang, Xingjun Ma, Sarah M. Erfani, James Bailey
2021 A* conf
Unlearnable Examples: Making Personal Data Unexploitable.
ICLR
Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang
2021 J jnl
Unlearnable Examples: Making Personal Data Unexploitable.
CoRR
Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang
2020 A* conf
Normalized Loss Functions for Deep Learning with Noisy Labels.
ICML
Xingjun Ma, Hanxun Huang, Yisen Wang, Simone Romano, Sarah M. Erfani, James Bailey
2020 J jnl
Normalized Loss Functions for Deep Learning with Noisy Labels.
CoRR
Xingjun Ma, Hanxun Huang, Yisen Wang, Simone Romano, Sarah M. Erfani, James Bailey