王金伟｜南开大学｜学者主页

2026

低投毒率下基于敏感度优化的隐形后门攻击

闫雷鸣，吉丽菁，王金伟

《计算机科学》

2026

对抗样本生成、防御与应用研究综述

Jiawei Zhang, Hao Wu, Lin Yuan, Hao Wang, Xin Cheng, Xiangyang Luo, Bin Ma, Jinwei Wang

Journal of Image and Graphics

DOI

2026

基于异构特征协同的轻量化恶意软件分类方法

陈治国，赵攀，谢雪，郑文鑫，王金伟

《通信学报》

2026

Obfuscation-resilient malware classification via spatial perception and multi-granular attention collaboration

Zhiguo Chen, Tao Lu, Wenxin Zheng, Jinwei Wang, Sung-Ryul Kim, Wei-Zhi Meng

Expert systems with applications

DOI

2026

Re-Cropping Framework: A Grid Recovery Method for Quantization Step Estimation in Non-Aligned Recompressed Images

Xin Cheng, Hao Wang, Xiang-Yang Luo, Qingxiao Guan, Bin Ma, Jinwei Wang

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

DOI

2026

HENet: A Heterogeneous Encoding Network for General and Robust Adversarial Example Generation

Jiawei Zhang, Hao Wang, Hao Wu, B. Li, Xiangyang Luo, Bin Ma, Jinwei Wang

IEEE Transactions on Information Forensics and Security

DOI

2026

JPEG Compression Simulation Invertible Neural Network for Robust Image Steganography

Kun Li, Weike You, B. Ma, Zhong-Liang Yang, Linna Zhou, Jinwei Wang

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

DOI

2026

A survey on JPEG image forensics: Exploring key advances and persistent challenges in compression and quantization analysis

Hao Wang, Hao Wang, Xin Cheng, Jiawei Zhang, HAO WU, Xue Dong Xie, Xiangyang Luo, Bin Ma, Jinwei Wang

Computers & Security

DOI

2026

Rethinking Cross-Table Quantization Step Estimation: From Global and Local Perspectives

Xin Cheng, Hao Wang, Xiangyang Luo, Bin Ma, Baowei Wang, Bin Li, Jinwei Wang

IEEE Transactions on Information Forensics and Security

DOI

2026

Advancements in adversarial example defense for deep learning models: a review

Ruipu Ma, Yi Zhang, Jinwei Wang, Wei Lu, Xiangyang Luo

Cybersecurity

DOI

2025

基于GAN网络图像语义指导的取证修复图像模型

王金伟，张子荷，罗向阳，马宾

《信息安全学报》

DOI

2025

基于多伪造模型对抗优化的鲁棒图像扰动

穆文鹏，王金伟，陈北京，聂丽娜，莫皓岚，徐菲

《信息安全学报》

DOI

2025

基于增强灰度共生矩阵的深度恶意代码可视化分类方法

王金伟，陈正嘉，谢雪，罗向阳，马宾

《信息安全学报》

DOI

2025

DVW: Diffusion Visible Watermark

Jiawei Zhang, Xiaoli Jiang, Hao Wang, Lin Yuan, Xiangyang Luo, Bin Ma, Jinwei Wang

ACM Multimedia

DOI

2025

A dual-stream model based on PRNU and quaternion RGB for detecting fake faces

Mohan Hua, Shuangliang Li, Jinwei Wang

PLoS ONE

DOI

2025

LDSGAN: Unsupervised Image‐to‐Image Translation With Long‐Domain Search GAN for Generating High‐Quality Anime Images

Hao Wang, Chen-Bin Wang, Xin Cheng, Hao Wu, Jiawei Zhang, Jinwei Wang, Xiangyang Luo, Bin Ma

International Journal of Intelligent Systems

DOI

2025

A GAN-based anti-forensics method by modifying the quantization table in JPEG header file

Hao Wang, Hao Wang, Xin Cheng, Hao Wu, Xiangyang Luo, Bin Ma, Hui Zong, Jinwei Wang, Jinwei Wang

Journal of Visual Communication and Image Representation

DOI

2025

Defense Against Adversarial Faces at the Source: Strengthened Faces Based on Hidden Disturbances

Shuangliang Li, Jinwei Wang, Hao Wu, Jiawei Zhang, Xin Cheng, Xiangyang Luo, Bin Ma

IEEE Transactions on Artificial Intelligence

DOI

2024

基于双曲正切和矩的免疫防御

吴昊，王金伟，罗向阳，马宾

《计算机学报》

2024

JPEG量化步长估计综述

程鑫，王金伟，王昊，罗向阳，李晓龙，朱国普，马宾

《信息安全学报》

2024

基于强化样本的伪孪生网络图像篡改定位模型

王金伟，张子荷，罗向阳，马宾

《网络与信息安全学报》

2024

彩色图像隐写分析研究进展

徐萌，罗向阳，王金伟，王昊

《网络与信息安全学报》

2024

针对BMP格式掩盖的JPEG同步重压缩检测方法

王金伟，王伟，王昊，罗向阳，马宾

《软件学报》

2024

基于Ngram-TFIDF的深度恶意代码可视化分类方法

王金伟，陈正嘉，谢雪，罗向阳，马宾

《通信学报》

2024

《中国图象图形学报》数字媒体深度伪造与对抗专栏简介

卢伟，钱振兴，罗向阳，赵险峰，李晓龙，张卫明，李斌，王员根，王金伟，秦川，陈秀妍

《中国图象图形学报》

2024

Boosting Adversarial Training with Learnable Distribution

Kai Chen, Jinwei Wang, James Msughter Adeke, Guang-Jie Liu, Yuewei Dai

Computers, Materials & Continua

DOI

2024

Generating Image Adversarial Example by Modifying JPEG Stream

Junjie Zhao, Sen Qiao, Jinwei Wang, Guangjie Liu

CVDL

DOI

2024

Advancing Quantization Steps Estimation: A Two-Stream Network Approach for Enhancing Robustness

Xin Cheng, Hao Wang, Jinwei Wang, Xiangyang Luo, Bin Ma

ACM International Conference on Multimedia (ACM MM)

DOI

2023

基于多质量因子压缩误差的对抗样本攻击方法识别

赵俊杰，王金伟，吴俊凤

《中国图象图形学报》

2023

基于空频联合卷积神经网络的GAN生成人脸检测

王金伟，曾可慧，张家伟，罗向阳，马宾

《计算机科学》

2023

基于超像素滤波的非对称失真隐写方法

朱利妍，罗向阳，张祎，王金伟，卢伟，刘粉林

《计算机学报》

2023

恶意软件检测和分类可视化技术综述

王金伟，陈正嘉，谢雪，罗向阳，马宾

《网络与信息安全学报》

2023

基于解压缩模块的JPEG同步重压缩检测

王金伟，胡冰涛，张家伟，马宾，罗向阳

《电子学报》

2022

数字图像鲁棒隐写综述

张祎，罗向阳，王金伟，卢伟，杨春芳，刘粉林

《中国图象图形学报》

2021

基于SmsGAN的对抗样本修复

赵俊杰，王金伟

《郑州大学学报(工学版)》

DOI

2018

一种基于改进乒乓协议的量子隐写术

王金伟，朱天成，瞿治国

《计算机工程》

2016

基于分数阶四元数傅里叶变换的彩色图像自适应水印算法

王金伟，周春飞，王水平，陈北京，孙星明

《电子与信息学报》

2007

基于3维提升可分离小波变换的图像水印方案(英文)

王金伟，刘光杰，戴跃伟，王执铨

《中国图象图形学报》

2006

鲁棒与半脆弱的数字水印研究

王金伟

《南京理工大学》

精选作品

期刊论文

低投毒率下基于敏感度优化的隐形后门攻击

对抗样本生成、防御与应用研究综述

基于异构特征协同的轻量化恶意软件分类方法

Obfuscation-resilient malware classification via spatial perception and multi-granular attention collaboration

Re-Cropping Framework: A Grid Recovery Method for Quantization Step Estimation in Non-Aligned Recompressed Images

HENet: A Heterogeneous Encoding Network for General and Robust Adversarial Example Generation

JPEG Compression Simulation Invertible Neural Network for Robust Image Steganography

A survey on JPEG image forensics: Exploring key advances and persistent challenges in compression and quantization analysis

Rethinking Cross-Table Quantization Step Estimation: From Global and Local Perspectives

Advancements in adversarial example defense for deep learning models: a review

基于GAN网络图像语义指导的取证修复图像模型

基于多伪造模型对抗优化的鲁棒图像扰动

基于增强灰度共生矩阵的深度恶意代码可视化分类方法

DVW: Diffusion Visible Watermark

A dual-stream model based on PRNU and quaternion RGB for detecting fake faces

LDSGAN: Unsupervised Image‐to‐Image Translation With Long‐Domain Search GAN for Generating High‐Quality Anime Images

A GAN-based anti-forensics method by modifying the quantization table in JPEG header file

Defense Against Adversarial Faces at the Source: Strengthened Faces Based on Hidden Disturbances

基于双曲正切和矩的免疫防御

JPEG量化步长估计综述

基于强化样本的伪孪生网络图像篡改定位模型

彩色图像隐写分析研究进展

针对BMP格式掩盖的JPEG同步重压缩检测方法

基于Ngram-TFIDF的深度恶意代码可视化分类方法

《中国图象图形学报》数字媒体深度伪造与对抗专栏简介

Boosting Adversarial Training with Learnable Distribution

Generating Image Adversarial Example by Modifying JPEG Stream

Advancing Quantization Steps Estimation: A Two-Stream Network Approach for Enhancing Robustness

基于多质量因子压缩误差的对抗样本攻击方法识别

基于空频联合卷积神经网络的GAN生成人脸检测

基于超像素滤波的非对称失真隐写方法

恶意软件检测和分类可视化技术综述

基于解压缩模块的JPEG同步重压缩检测

数字图像鲁棒隐写综述

基于SmsGAN的对抗样本修复

一种基于改进乒乓协议的量子隐写术

基于分数阶四元数傅里叶变换的彩色图像自适应水印算法

基于3维提升可分离小波变换的图像水印方案(英文)

鲁棒与半脆弱的数字水印研究

会议论文

一种置换DCT域中频系数的盲水印算法

预印本

IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation

HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection

Immune Defense: A Novel Adversarial Defense Mechanism for Preventing the Generation of Adversarial Examples

Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks

Digital image splicing detection based on Markov features in QDCT and QWT domain

研究方向