郑海斌

郑海斌，男，中共党员，博士，现任浙江工业大学讲师，主要从事人工智能安全、大数据挖掘、计算机视觉图像处理、对抗攻防方向研究，在IEEE TDSC、ICSE 2022、IEEE TCSS、Information Sciences、Computers & Security、计算机研究与发展、软件学报、自动化学报等国内外重要会议和期刊上发表论文20余篇，其中包括以第一作者发表10篇，以通讯作者发表论文6篇，授权专利10项，受理专利20余项，同时担任IEEE TCSS、IEEE TNSE等期刊的审稿人。主持全军共用信息系统装备预研项目、国防科技大学安全模型开发链项目、陆军工程大学渗透测试项目等。

一作论文

1. Haibin Zheng, Jinyin Chen, Hang Du, Weipeng Zhu, Shouling Ji, and Xuhong Zhang*. GRIP-GAN: An Attack-Free Defense based on General Robust Inverse Perturbation[J]. IEEE Transactions on Dependable and Secure Computing, 2022: 19 (6), 4204-4224. (CCF-A期刊)

   https://ieeexplore.ieee.org/abstract/document/9599477

2. Haibin Zheng, Zhiqing Chen, Tianyu Du, Xuhong Zhang, Yao Cheng, Shouling Ji, Jingyi Wang and Jinyin Chen*. NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification[C]. In Proceedings of the 44th International Conference on Software Engineering (ICSE '22). Association for Computing Machinery, New York, NY, USA, 1519–1531. (CCF-A会议)

   https://dl.acm.org/doi/abs/10.1145/3510003.3510123

3. Haibin Zheng, Jinyin Chen, Haibo Jin. CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space[C], IEEE/ACM International Conference on Automated Software Engineering (ASE) 2023. (CCF-A会议)

4. Haibin Zheng, Xiaohao Li, Jinyin Chen, Jianfeng Dong, Yan Zhang, Changting Lin*. One4All: Manipulate One Agent to Poison the Cooperative Multi-Agent Reinforcement Learning[J]. Computers & Security, 2023: 124, 1-15. (SCI 2区, CCF-B)

   https://www.sciencedirect.com/science/article/pii/S0167404822003972

5. Haibin Zheng, Jinyin Chen, Wenchang Shangguan, Zhaoyan Ming, Xing Yang, Zhijun Yang. GONE: A Generic O(1) NoisE Layer for Protecting Privacy of Deep Neural Networks[J]. Computers & Security, 2023. (SCI 2区, CCF-B, IF: 5.105)

6. Haibin Zheng, Haiyang Xiong, Haonan Ma, Guohan Huang, Jinyin Chen*. Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection [J]. IEEE Transactions on Computational Social Systems, 2023. (SCI 2区)

7. Haibin Zheng, Haiyang Xiong, Jinyin Chen*, Haonan Ma, Guohan Huang. Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs [J]. IEEE Transactions on Computational Social Systems, 2023. (SCI 2区)

8. Haibin Zheng, Tao Liu, Rongchang Li and Jinyin Chen*. PoE: Poisoning Enhancement Through Label Smoothing in Federated Learning [J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2023 (SCI 2区)

9. 郑海斌,陈晋音,章燕,张旭鸿,葛春鹏,刘哲,欧阳亦可,纪守领*. 面向自然语言处理的对抗攻防与鲁棒性分析综述[J]. 计算机研究与发展, 2021, 58(8): 1727-1750. DOI: 10.7544/issn1000-1239.2021.20210304.（CCF-A中文）

通讯作者论文

1. Jinyin Chen, Haibin Zheng*, Tao Liu, Jiawei Liu, Yao Cheng, Xuhong Zhang, and Shouling Ji. EdgePro: Edge Deep Learning Model Protection via Neuron Authorization[J]. IEEE Transactions on Dependable and Secure Computing (TDSC), DOI: 10.1109/TDSC.2024.3365730, 2024. (CCF-A期刊)

2. Jinyin Chen, Jie Ge, Haibin Zheng*. ActGraph: Prioritization of Test Cases Based on Deep Neural Network Activation Graph[J], Automated Software Engineering, 2023. (SCI)

3. Jinyin Chen, Guohan Huang, Haibin Zheng*, Shanqing Yu, Wenrong Jiang and Chen Cui. Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning[J]. IEEE Transactions on Computational Social Systems (TCSS), 2022. (SCI)

4. Jinyin Chen, Guohan Huang, Haibin Zheng*, Dunjie Zhang, Xiang Lin. Graphfool: Targeted Label Adversarial Attack on Graph Embedding[J]. IEEE Transactions on Computational Social Systems (TCSS), 2022. (SCI)

5. 李荣昌,刘涛,郑海斌*,陈晋音,刘振广,基于最大最小策略的纵向联邦学习隐私保护方法,自动化学报,2022 (CCF-A中文EI）

博士期间论文（学生一作）

1. Jinyin Chen, Haibin Zheng, Wenchang Shangguan, Liangying Liu, Shouling Ji. ACT-Detector: Adaptive Channel Transformation-based Light-Weighted Detector for Adversarial Attacks[J]. Information Sciences (INS), 2021, 564: 163-192. DOI: 10.1016/j.ins.2021.01.035 (SCI 1区, TOP期刊, IF: 8.233)（导师一作）

2. Jinyin Chen, Haibin Zheng, Hui Xiong, Shijing Shen, Mengmeng Su. MAG-GAN: Massive Attack Generator via GAN[J]. Information Sciences (INS), 2020, 536: 67-90. DOI: 10.1016/j.ins.2020.04.019. (SCI 1区, TOP期刊, IF: 8.233)（导师一作）

3. Jinyin Chen, Haibin Zheng, Hui Xiong, Ruoxi Chen, Tianyu Du, Zhen Hong, Shouling Ji. FineFool: A Novel DNN Object Contour Attack on Image Recognition based on the Attention Perturbation Adversarial Technique [J]. Computers & Security (COSE), 2021, 104: 102220. DOI: 10.1016/j.cose.2021.102220. (SCI 2区, CCF-B, IF: 4.573)（导师一作）

4. Jinyin Chen, Haibin Zheng, Ruoxi Chen, Hui Xiong. RCA-SOC: A Novel Adversarial Defense by Refocusing on Critical Areas and Strengthening Object Contours[J]. Computers & Security (COSE), 2020, 96: 101916. DOI: 10.1016/j.cose.2020.101916. (SCI 2区, CCF-B, IF: 5.105)（导师一作）

5. Jinyin Chen, Haibin Zheng, Hui Xiong, Yangyang Wu, Xiang Lin, Shiyan Ying, Qi Xuan. DGEPN-GCEN2V: A New Framework for Mining GGI and Its Application in Biomarker Detection[J]. SCIENCE CHINA Information Sciences (SCIS), 2019, 61: 050108. DOI: 10.1007/s11432-018-9704-7. (SCI 2区, CCF-B, IF: 2.731)（导师一作）

6. Jinyin Chen, Haibin Zheng, Xiang Lin, Yangyang Wu, Mengmeng Su. A Novel Image Segmentation Method Based on Fast Density Clustering Algorithm[J]. Engineering Applications of Artificial Intelligence (EAAI), 2018, 73: 92-110. DOI: 10.1016/j.engappai.2018.04.023. (SCI 2区, CCF-C, IF: 3.640)（导师一作）

7. Jinyin Chen, Haibin Zheng, Mengmeng Su, Tianyu Du, Changting Lin, Shouling Ji. Invisible Poisoning: Highly Stealthy Targeted Poisoning Attack[C]. Proceedings of the 15th International Conference on Information Security and Cryptology (Inscrypt 2019). Springer, Cham, 2019: 173-198. (EI: 20202208719133) (最佳论文)（导师一作）

授权专利

1. 陈晋音, 郑海斌, 等. 基于灰度峰值的裂缝位置查找方法. ZL 201610115242.4

2. 陈晋音, 郑海斌, 等. 一种基于快速密度聚类算法的图像分割方法. ZL 201610887803.2

3. 陈晋音, 郑海斌, 等. 基于深度学习和进化计算的特征基因选择方法. ZL 201711336535.6

4. 陈晋音, 郑海斌, 等. 基于可视图算法的基因表达时序数据分类方法. ZL 201810386434.8

5. 陈晋音, 郑海斌, 等. 基于流形学习与闭环深度卷积双网络模型的基因特征提取方法. ZL 201710355356.0

6. 陈晋音, 郑海斌, 等. 基于对抗式生成网络的深度学习对抗性攻击防御方法. ZL 201810141210.0.

7. 陈晋音, 郑海斌, 等. 基于数据流聚类的癌症亚型精准发现与演化分析方法. ZL 201710355340.X

8. 陈晋音, 郑海斌, 等. 基于RNN的基因调控网络构建与动态差异性分析方法. ZL 201710355357.5

9. 陈晋音, 郑海斌, 等. 一种基于LSTM的分级式无线信号调制类型识别方法. ZL 201910089087.7

10. 陈晋音, 郑海斌, 等. 一种基于特征重映射的对抗样本防御方法和应用. ZL 202010115357.X

11. 陈晋音, 成凯回, 郑海斌. 基于通道检测的面向无线信号识别的对抗攻击防御方法与装置. ZL 201911031922.8

1. 国家自然科学基金委青年基金项目, 智能算法的偏见测试与纠偏研究, 62406286, 2025/1-2027/12, 在研, 主持

2. **单位***部, 全军共用信息系统装备预研项目, *********, 智能模型*********控制技术, 2023-07 至 2025-12, 在研, 主持

3. **单位***部, 全军共用信息系统装备预研项目, *********, 智能模型*******验证技术, 2023-07 至 2025-12, 在研, 主持

4. 杭州熔合智造科技有限公司, 科研外协项目, KYY-HX-20230425, 智能算法模型产权防护技术研发, 2023-06 至 2025-05, 在研, 主持

5. 浙江大学, 科研外协项目, JG-WA-2023029, 智能感知算法模型基础环境构建和数据加工测试, 2023-11 至 2024-12, 在研, 主持

6. 国防科技大学, 科研外协项目, JG-WA-2024002, 基于图像感知的智能软件开发链环境构建, 2023-12 至 2024-03, 结题, 主持

7. 陆军工程大学, 科研外协项目, 2022-JLGCZYJY-F9001, 多智能体协同渗透平台, 2022-11 至 2023-05, 结题, 主持

1 第八届“西湖科创杯”中国研究生智慧城市技术与创意设计大赛一等奖

项目名称：基于深度学习的智能驾驶安全研究

指导学生：贾澄钰（2021级）、严云杰（2022级）、蔡龙钐（2022级）

时间：2023年03月

1 人工智能概论 2023/2024(1)

开课部门：计算机科学与技术学院，课程号：G126824；课程性质：选修课，课程类别：专业课程

https://www.icourse163.org/spoc/course/ZJUT-1469756163?from=searchPage&outVendor=zw_mooc_pcssjg_