胡清元｜江南大学｜学者主页

期刊论文

2024

Towards Gradient-Based Saliency Consensus Training for Adversarial Robustness

Qian Li, Chao Shen, Qingyuan Hu, Chenhao Lin, Xiang Ji, Sai-Yu Qi

IEEE Transactions on Dependable and Secure Computing

DOI

2024

Attention-SA: Exploiting Model-Approximated Data Semantics for Adversarial Attack

Qian Li, Qingyuan Hu, Haoran Fan, Chenhao Lin, Chao Shen, Li-Bing Wu

IEEE Transactions on Information Forensics and Security

DOI

2023

Revisiting Gradient Regularization: Inject Robust Saliency-Aware Weight Bias for Adversarial Defense

Qian Li, Qingyuan Hu, Chenhao Lin, Di Wu, Chao Shen

IEEE Transactions on Information Forensics and Security

DOI

2023

Cross-Region Feature Reformer with Semantic Preservation for Adversarial Android Malware Detection

Qian Li, Qingyuan Hu, Di Wu, Sai-Yu Qi, Yong Qi, Wei Wei, Nai-Xue N. Xiong

Social Science Research Network

DOI

2022

Stochastic Ghost Batch for Self-distillation with Dynamic Soft Label

Qian Li, Qingyuan Hu, Sai-Yu Qi, Yong Qi, Di Wu, Yun Lin, Jin-Song Dong

Knowledge-Based Systems

DOI

2022

Can Model Compression Improve NLP Fairness

Guangxuan Xu, Qingyuan Hu

arXiv.org

2022

Learning Action Conditions from Instructional Manuals for Instruction Understanding

Te-Lin Wu, Caiqi Zhang, Qingyuan Hu, Alexander Spangher, Nanyun Peng

Annual Meeting of the Association for Computational Linguistics

DOI

2022

Correction to: Multi-level word features based on CNN for fake news detection in cultural communication

Qingyuan Hu, Q. Li, You-Shui Lu, Yue Yang, Jing-Xian Cheng

Personal and Ubiquitous Computing

DOI

2021

Modeling Fuzzy Cluster Transitions for Topic Tracing

X. Jing, Yi Zhang, Qingyuan Hu, J. Rayz

Annual Conference on the North American Fuzzy Information Processing Society

DOI

2021

Semi-supervised two-phase familial analysis of Android malware with normalized graph embedding

Qian Li, Qingyuan Hu, Yong Qi, Sai-Yu Qi, Xinxing Liu, Pengfei Gao

Knowledge-Based Systems

DOI

2021

Tracing Topic Transitions with Temporal Graph Clusters

X. Jing, Qingyuan Hu, Yi Zhang, J. Rayz

The Florida AI Research Society

DOI

2021

Adversarial Adaptive Neighborhood With Feature Importance-Aware Convex Interpolation

Qian Li, Yong Qi, Qingyuan Hu, Sai-Yu Qi, Yun Lin, J. Dong

IEEE Transactions on Information Forensics and Security

DOI

2020

Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference

Qingyuan Hu, Yi Zhang, Kanishka Misra, J. Rayz

IEEE International Conference on Cognitive Informatics and Cognitive Computing

DOI

2020

Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer

Qian Li, Qingyuan Hu, Yong Qi, Sai-Yu Qi, Jie Ma, Jian Zhang

International Joint Conference on Artificial Intelligence

DOI

2019

Multi-level word features based on CNN for fake news detection in cultural communication

Qingyuan Hu, Q. Li, You-Shui Lu, Yue Yang, Jing-Xian Cheng

Personal and Ubiquitous Computing

DOI

会议论文

2021

A Survey Of Adversarial Example Toolboxes

Qingyuan Hu

Proceedings of the 2nd International Conference on Computing and Data Science (CONF-CDS 2021)

DOI

胡清元

精选作品

期刊论文

Towards Gradient-Based Saliency Consensus Training for Adversarial Robustness

Attention-SA: Exploiting Model-Approximated Data Semantics for Adversarial Attack

Revisiting Gradient Regularization: Inject Robust Saliency-Aware Weight Bias for Adversarial Defense

Cross-Region Feature Reformer with Semantic Preservation for Adversarial Android Malware Detection

Stochastic Ghost Batch for Self-distillation with Dynamic Soft Label

Can Model Compression Improve NLP Fairness

Learning Action Conditions from Instructional Manuals for Instruction Understanding

Correction to: Multi-level word features based on CNN for fake news detection in cultural communication

Modeling Fuzzy Cluster Transitions for Topic Tracing

Semi-supervised two-phase familial analysis of Android malware with normalized graph embedding

Tracing Topic Transitions with Temporal Graph Clusters

Adversarial Adaptive Neighborhood With Feature Importance-Aware Convex Interpolation

Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference

Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer

Multi-level word features based on CNN for fake news detection in cultural communication

会议论文

A Survey Of Adversarial Example Toolboxes

研究方向