杨兴浩｜中国石油大学(华东)｜学者主页

2026

Discrete multi-head training with rule-based perturbation location for accurate text defense

Zikai Wang, Xinghao Yang, Baodi Liu, Wei Liu, Weifeng Liu

Pattern Recognition

DOI

2026

Safety Anchor-Guided Adaptive Bias Decay for Jailbreak Defense

Zikai Wang, Xinghao Yang, Bingfeng Zhang, Weifeng Liu

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2026

Multiobjective Simulated Annealing-Based Stopwords Substitution for Rubbish Text Attack

Chen Li, Xinghao Yang, Ao Wang, Yongshun Gong, Baodi Liu, Weifeng Liu

IEEE Transactions on Neural Networks and Learning Systems

DOI

2026

Intermediate-Layer Filtering for Text Backdoor Defense

J Wang, Xinghao Yang, Baodi Liu, Weifeng Liu

DOI

2026

Semantic-Preserving Phrase-Insertion Universal Adversarial Attack against Vision-Language Pre-training Models

Yueyan Zhou, Weifeng Liu, Xinghao Yang, Baodi Liu

DOI

2026

Separate-Align Embedding Based Backdoor Attacks in Large Language Model-based Agents

Jiahao Qin, Xinghao Yang, Baodi Liu, Weifeng Liu

DOI

2026

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance

Ao Wang, Xinghao Yang, Yongshun Gong, Wei Liu, Baodi Liu, Weifeng Liu

Annual Meeting of the Association for Computational Linguistics (ACL)

DOI

2026

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance

Association for Computational Linguistics 2026, Yongshun Gong, Wei Liu, Weifeng Liu, Baodi Liu, Ao Wang, Xinghao Yang

Underline Science Inc.

DOI

2025

构建基于语言感知指令微调的精准翻译定制大语言模型（英文）

昝畅通，丁亮，沈力，詹忆冰，杨兴浩，刘伟锋

ENGINEERING Information Technology & Electronic Engineering

2025

Unstable Sample based Style Enhancement for Invisible Text Backdoor Attack

Jiahao Qin, Xinghao Yang, Baodi Liu

International Conference on New Trends in Computational Intelligence (NTCI)

DOI

2025

Building accurate translation-tailored large language models with language-aware instruction tuning

Changtong Zan, Liang Ding, Li Shen, Yibing Zhan, Xinghao Yang, Weifeng Liu

Frontiers of Information Technology & Electronic Engineering

DOI

2025

Correction: Parentheses insertion based sentence-level text adversarial attack

Ang Li, Xinghao Yang, Baodi Liu, Honglong Chen, Dapeng Tao, Weifeng Liu

Multimedia Systems

DOI

2025

Parentheses insertion based sentence-level text adversarial attack

Ang Li, Xinghao Yang, Baodi Liu, Honglong Chen, Dapeng Tao, Weifeng Liu

Multimedia Systems

DOI

2025

Disentangled Information Bottleneck for Adversarial Text Defense

Yidan Xu, Xinghao Yang, Wei Liu, Baodi Liu, Weifeng Liu

Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI

2024

Short-time Fourier Inversion Based Multi-band Generation for Efficient Synthetic Speech Attack

Haolu Sun, Xinghao Yang, Baodi Liu, Weifeng Liu

International Conference on New Trends in Computational Intelligence (NTCI)

DOI

2024

SSEAP: Semantic-Syntactic Enhanced Adversarial Repair for Universal Text Defense

Hongliang Liu, Xinghao Yang, Baodi Liu, Weifeng Liu

International Conference on New Trends in Computational Intelligence (NTCI)

DOI

2024

Weight Saliency search with Semantic Constraint for Neural Machine Translation attacks

Wen Han, Xinghao Yang, Baodi Liu, Kai Zhang, Weifeng Liu

Pattern Recognition Letters

DOI

2024

Edit-based adversarial text attack

Ang Li, Xinghao Yang, Weifeng Liu

International Conference on Computer Information and Big Data Applications (CIBDA)

DOI

2024

Adaptive Gradient-based Word Saliency for adversarial text attacks

Yupeng Qi, Xinghao Yang, Baodi Liu, Baodi Liu, Kai Zhang, Weifeng Liu

Neurocomputing

DOI

2024

Gradient-guided Simulated Annealing for Insensitivity-based Text Attack

C. C. Li, Xinghao Yang, Baodi Liu, Weifeng Liu

DOI

2024

MGBS: Multi-granularity Beam Search for NMT Model Attack

Wen Han, Xinghao Yang, Baodi Liu, Weifeng Liu

DOI

2024

Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks

Ao Wang, Xinghao Yang, Li Chen, Baodi Liu, Weifeng Liu

Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI

2023

Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation

Chen Li, Xinghao Yang, Bao-Di Liu, Wei-Feng Liu, Honglong Chen

International Joint Conference on Artificial Intelligence

DOI

2023

Generation-based parallel particle swarm optimization for adversarial text attacks

Xinghao Yang, Yupeng Qi, Honglong Chen, Bao-Di Liu, Wei-Feng Liu

Information Sciences

DOI

2023

Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition (Extended Abstract)

Xinghao Yang, Wei-Feng Liu, W. Liu

IEEE International Conference on Data Engineering

DOI

2023

Adversarial Machine Learning: Attack Surfaces, Defence Mechanisms, Learning Theories in Artificial Intelligence

Aneesh Sreevallabh Chivukula, Xinghao Yang, B. Liu, Wei Liu, Wan-Lei Zhou

DOI

2023

Self-Paced Hard Task-Example Mining for Few-Shot Classification

Renjie Xu, Xinghao Yang, Xingxing Yao, Da-Peng Tao, Wei-Jia Cao, Xiaoping Lu, Wei-Feng Liu

IEEE transactions on circuits and systems for video technology (Print)

DOI

2023

GSA4FDA: Deep Geometric and Statistic Alignment for Fewer Labeled Domain Adaptation

Yuying Cai, Bao-Di Liu, Xinghao Yang, Xiaoping Lu, Da-Peng Tao, Wei-Feng Liu

Neural Processing Letters

DOI

2023

MCNet: Magnitude consistency network for domain adaptive object detection under inclement environments

Jian Pang, Weifeng Liu, Bingfeng Zhang, Xinghao Yang, Baodi Liu, Dapeng Tao

Pattern Recognition

DOI

2023

Generating Prompt-Based Adversarial Text Examples via Variable Neighborhood Search

Yupeng Qi, Xinghao Yang, Baodi Liu, Kai Zhang, Weifeng Liu

China Automation Congress (CAC)

DOI

2023

Semantic-Preserving Adversarial Text Attacks

Xinghao Yang, Yongshun Gong, Weifeng Liu, James Bailey, Tianqing Zhu, Dacheng Tao, Wei Liu

IEEE Transactions on Sustainable Computing

DOI

2022

Selecting task with optimal transport self-supervised learning for few-shot classification

Renjie Xu, Xinghao Yang, Bao-Di Liu, Kai Zhang, Wei-Feng Liu

arXiv.org

DOI

2021

基于视频智能化分析的智慧城管平台

叶逢春，杨兴浩

《电子技术与软件工程》

2020

Population Location and Movement Estimation through Cross-domain Data Analysis

Xinghao Yang, W. Liu

International Joint Conference on Artificial Intelligence

DOI

2020

Targeted Attention Attack on Deep Learning Models in Road Sign Recognition

Xinghao Yang, Wei-Feng Liu, Sheng-Li Zhang, Wei Liu, D. Tao

IEEE Internet of Things Journal

DOI

2020

Tensor Canonical Correlation Analysis Networks for Multi-View Remote Sensing Scene Recognition

Xinghao Yang, Wei-Feng Liu, Wei Liu

IEEE Transactions on Knowledge and Data Engineering

DOI

2020

Game Theoretical Adversarial Deep Learning With Variational Adversaries

A. Chivukula, Xinghao Yang, Wei Liu, Tian-Qing Zhu, Wan-Lei Zhou

IEEE Transactions on Knowledge and Data Engineering

DOI

2019

Adversarial Deep Learning with Stackelberg Games

A. Chivukula, Xinghao Yang, Wei Liu

International Conference on Neural Information Processing

DOI

2019

A Survey on Canonical Correlation Analysis

Xinghao Yang, Weifeng Liu, Wei Liu, D. Tao

IEEE Transactions on Knowledge and Data Engineering

DOI

2018

基于典型相关分析的多视角图像识别算法研究

杨兴浩

《中国石油大学(华东)》

2018

Multiview dimension reduction via Hessian multiset canonical correlations

Weifeng Liu, Xinghao Yang, Da-Peng Tao, Jun Cheng, Yuanyan Tang

Information Fusion

DOI

2018

The comparison of different graph convolutional neural networks for image recognition

Si-Chao Fu, Xinghao Yang, Weifeng Liu

International Conference on Internet Multimedia Computing and Service

DOI

2017

Multiview Canonical Correlation Analysis Networks for Remote Sensing Image Recognition

Xinghao Yang, Weifeng Liu, Da-Peng Tao, Jun Cheng, Shuying Li

IEEE Geoscience and Remote Sensing Letters

DOI

2017

Canonical correlation analysis networks for two-view image recognition

Xinghao Yang, Weifeng Liu, Da-Peng Tao, Jun Cheng

Information Sciences

DOI

2017

Multiple Scale Canonical Correlation Analysis Networks for Two-View Object Recognition

Xinghao Yang, Weifeng Liu

International Conference on Neural Information Processing

DOI

2015

Sparse principle motion component for one-shot gesture recognition

Xinghao Yang, Hongli Liu, Weifeng Liu, Zheng-Jun Zha

International Conference on Internet Multimedia Computing and Service

DOI

精选作品

期刊论文

Discrete multi-head training with rule-based perturbation location for accurate text defense

Safety Anchor-Guided Adaptive Bias Decay for Jailbreak Defense

Multiobjective Simulated Annealing-Based Stopwords Substitution for Rubbish Text Attack

Intermediate-Layer Filtering for Text Backdoor Defense

Semantic-Preserving Phrase-Insertion Universal Adversarial Attack against Vision-Language Pre-training Models

Separate-Align Embedding Based Backdoor Attacks in Large Language Model-based Agents

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance

构建基于语言感知指令微调的精准翻译定制大语言模型（英文）

Unstable Sample based Style Enhancement for Invisible Text Backdoor Attack

Building accurate translation-tailored large language models with language-aware instruction tuning

Correction: Parentheses insertion based sentence-level text adversarial attack

Parentheses insertion based sentence-level text adversarial attack

Disentangled Information Bottleneck for Adversarial Text Defense

Short-time Fourier Inversion Based Multi-band Generation for Efficient Synthetic Speech Attack

SSEAP: Semantic-Syntactic Enhanced Adversarial Repair for Universal Text Defense

Weight Saliency search with Semantic Constraint for Neural Machine Translation attacks

Edit-based adversarial text attack

Adaptive Gradient-based Word Saliency for adversarial text attacks

Gradient-guided Simulated Annealing for Insensitivity-based Text Attack

MGBS: Multi-granularity Beam Search for NMT Model Attack

Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks

Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation

Generation-based parallel particle swarm optimization for adversarial text attacks

Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition (Extended Abstract)

Adversarial Machine Learning: Attack Surfaces, Defence Mechanisms, Learning Theories in Artificial Intelligence

Self-Paced Hard Task-Example Mining for Few-Shot Classification

GSA4FDA: Deep Geometric and Statistic Alignment for Fewer Labeled Domain Adaptation

MCNet: Magnitude consistency network for domain adaptive object detection under inclement environments

Generating Prompt-Based Adversarial Text Examples via Variable Neighborhood Search

Semantic-Preserving Adversarial Text Attacks

Selecting task with optimal transport self-supervised learning for few-shot classification

基于视频智能化分析的智慧城管平台

Population Location and Movement Estimation through Cross-domain Data Analysis

Targeted Attention Attack on Deep Learning Models in Road Sign Recognition

Tensor Canonical Correlation Analysis Networks for Multi-View Remote Sensing Scene Recognition

Game Theoretical Adversarial Deep Learning With Variational Adversaries

Adversarial Deep Learning with Stackelberg Games

A Survey on Canonical Correlation Analysis

基于典型相关分析的多视角图像识别算法研究

Multiview dimension reduction via Hessian multiset canonical correlations

The comparison of different graph convolutional neural networks for image recognition

Multiview Canonical Correlation Analysis Networks for Remote Sensing Image Recognition

Canonical correlation analysis networks for two-view image recognition

Multiple Scale Canonical Correlation Analysis Networks for Two-View Object Recognition

Sparse principle motion component for one-shot gesture recognition

会议论文

Pose estimation of non-cooperative spacecraft based on Convelutional Neural Network

研究方向