钱亚冠，教授、硕士生/博士生导师。2014年获浙江大学计算机专业博士学位。现任浙江科技大学大数据学院副院长，大数据学科负责人，海康威视边缘智能安全联合实验室主任，大数据与人工智能安全团队负责人。中国中文信息学会大数据安全与隐私计算专委会委员，全省智能物联网络与数据安全重点实验室特聘研究员。担任吴文俊人工智能科学技术奖评审专家，传感器技术与控制国际研讨会（ISSTC)执行主席，人工智能顶级会议AAAI程序委员会委员，国内外多个CCF推荐期刊和顶级会议的审稿人。主要研究方向为AI大模型安全、多模态深度学习、机器学习中的优化算法。近5年，围绕人工智能安全在ICCV、ECCV、AAAI等顶级会议，IEEE TIFS、IEEE TNNLS、ACM TOPS、ACM TKDD、软件学报、计算机研究与发展、电子学报等CCF推荐的重要期刊发表论文30多篇；授权发明专利7项；主持中央军委科技委创新特区项目（国家级），国家自然科学基金（面上）项目，浙江省自然科学基金（重点）项目，浙江省自然科学基金面上项目等纵向项目。认真指导并培养研究生18名，其中4名继续攻读博士学位。

欢迎访问大数据与人工智能安全实验室主页：https://lab.rjmart.cn/10366/AISecurityLab

一、发表的学术论文（一作或通讯）

[1] Yaguan Qian, Kecheng Chen, Bin Wang*, Zhaoquan Gu*, Shouling Ji, Wei Wang, Yanchun Zhang. “Enhancing Transferability of Adversarial Examples through Mixed-Frequency Inputs”, IEEE Transactions on Information Forensics and Security (TIFS). Early Access, 2024 (CCF A) (中科院 1区Top)

[2] Yaguan Qian*, Shuke He, Chenyu Zhao, Jiaqiang Sha, Wei Wang, Bin Wang. “LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions”, International Conference on Computer Vision (ICCV-23). Paris, France, 2023. (CCF A)  

[3]  钱亚冠, 马骏, 何念念, 王滨*, 顾钊铨, 凌祥, Wassim Swaileh. “面向边缘智能的两阶段对抗知识迁移方法”, 软件学报, 2022, 33(12). (中文CCF A)

[4]  钱亚冠, 何念念, 郭艳凯, 王滨*, 李晖, 顾钊铨, 张旭鸿, 吴春明. “针对深度神经网络模型指纹检测的逃避算法”, 计算机研究与发展, 2021, 58(5):1106-1117. (中文CCF A)

[5]  钱亚冠, 卢红波, 纪守领, 周武杰, 吴淑慧, 雷景生, 陶祥兴. “一种针对基于SVM入侵检测系统的毒性攻击方法”, 电子学报, 2019, 47(1):59-65. (中文CCF A)——入选领跑者5000中国精品科技期刊顶尖学术论文

[6]  Yaguan Qian, Shenghui Huang, Bin Wang*, Xiang Ling, Xiaohui Guan, Zhaoquan Gu, Shaoning Zeng, Wujie Zhou, Haijiang Wang. “Robust Network Architecture Search via Feature Distortion Restraining”, In Proc. of the 17th European Conference on Computer Vision (ECCV-22), Tel-Aviv, Israel, 2022. (CCF B)  

[7]  Zhiqiang He, Yaguan Qian*, Yuqi Wang, Bin Wang, Xiaohui Guan, Zhaoquan Gu, Xiang Ling, Shaoning Zeng, Haijiang Wang, Wujie Zhou. “Filter Pruning via Feature Discrimination in Deep Neural Networks”, In Proc. of the 17th European Conference on Computer Vision (ECCV-22), Tel-Aviv, Israel, 2022. (CCF B)

[8]  Yaguan Qian, Zhiqiang He, Yuqi Wang, Bin Wang*, Xiang Ling, Shaoning Zeng, Zhaoquan Gu, Haijiang Wang, and Wassim Swaileh. “Hierarchical Threshold Pruning Based on Uniform Response Criterion”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024, 35(8),  p.10869 - 10881. (CCF B) (中科院 1区Top)

[9]  Yaguan Qian, Danfeng Ma*, Bin Wang, Jun Pan, Jiamin Wang, Zhaoquan Gu, Jianhai Chen, Wujie Zhou, Jingsheng Lei. “Spot Evasion Attacks: Adversarial Examples for License Plate Recognition Systems with Convolutional Neural Networks”, Computers & Security (COSE), 95(2020), p.1-14. (CCF B) (中科院 2区)

[10]  Yaguan Qian, Yankai Guo, Qiqi Shao, Jiaming Wang, Bin Wang*, Zhaoquan Gu, Xiang Ling, Chunming Wu. “EI-MTD: Moving Target Defense for Edge Intelligence against Adversarial Attacks”, ACM Transactions on Privacy and Security (TOPS), 2022, 25(3), p.23-46. (CCF B) (中科院 3区)

[11]  Jiaoze Mao, Yaguan Qian*, Jianchang Huang, Zejie Lian, Renhui Tao, Bin Wang, Wei Wang, Tengteng Yao. “Object-free Backdoor Attack and Defense on Semantic Segmentation”. Computer & Security, 132(2023), p.1-15, 2023. (CCF B)  (中科院 3区)

[12] Yaguan Qian, Jiaming Wang, Haijiang Wang, Zhaoquan Gu, Bin Wang*, Shaoning Zeng, Wassim Swaileh. “Visually Imperceptible Adversarial Patch Attacks”. Computers & Security (COSE), 123(2022), p.1-11. (CCF B) (中科院 3区)

[13]  钱亚冠, 方科彬, 康明, 顾钊铨, 潘俊, 王滨*, Wassim Swaileh. “一种应用于文本分类的段落向量正向激励方法”, 中文信息学报, 2023, 37(7) (中文CCF B)

[14] Jianchang Huang, Yinyao Dai, Fang Lu, Bin Wang, Zhaoquan Gu, Boyang Zhou, Yaguan Qian*. “Denoising Deep Features of Convolutional Neural Networks against Adversarial Examples”, Applied Intelligence, 54(2): 1672-1690, 2024  (中科院 2区)

[15] Yinyao Dai, Yaguan Qian*, Fang Lu, Bin Wang*, Zhaoquan Gu, Wei Wang, Jian Wan, Yanchun Zhang. “Improving Adversarial Robustness of Medical Imaging Systems via Adding Global Attention Noise”. Computers in Biology and Medicine (CBM), 164(2023), p.1-11, 2023. (中科院 2区)

[16] Xiaoyu Liang, Yaguan Qian*, Jianchang Huang, Xiang Ling, Bin Wang, and Chunming Wu. “Towards Desirable Decision Boundary by Moderate-Margin Adversarial Training”. Pattern Recognition Letters (PRL), 173(2023), p.30-37, 2023. (中科院 3区)

[17]  Yaguan Qian, Xiaoyu Liang, Ming Kang, Bin Wang*, Xin Wang, Zhaoquan Gu, Chunming Wu. “GAAT: Group Adaptive Adversarial Training to Improve the Trade-Off between Robustness and Accuracy”. International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), 2022, 36(13): 1-26.  (中科院 4区)

[18]  Xiaohui Guan, Qiqi Shao, Yaguan Qian*, Tengteng Yao, Bin Wang. “Adversarial Training in Logit Space against Tiny Perturbations”. Multimedia Systems, 2023 (中科院 4区)

[19]  钱亚冠, 张锡敏, 王滨*, 顾钊铨, 李蔚, 云本胜. 基于二阶对抗样本的对抗训练防御, 电子与信息学报, 2021, 43(11):3367-3373. (浙大一级)

[20]  钱亚冠, 卢红波, 纪守领, 周武杰, 吴淑慧, 云本胜, 陶祥兴, 雷景生. “基于粒子群优化的对抗样本生成算法”, 电子与信息学报, 2019, 41(7):1658-1665. (浙大一级)

[21] Yaguan Qian, Liangjian Zhang, Yuqi Wang, Boyuan Ji, Tengteng Yao, Bin Wang*. “Developing Hessian-Free Second-Order Adversarial Examples for Adversarial Learning”. International Journal of Applied Mathematics and Computer Science, 34(3), 2024. (中科院 4区) 

二、与其他课题组合作发表的学术论文

[10] Hao Tan, Huan Zhang, Junjian Zhang, Yaguan Qian, Zhaoquan Gu. DualPure: An Efficient Adversarial Purification Method for Speech Command Recognition, Conference of the International Speech Communication Association (InterSpeech 2024)

[9] Xiangyu Wei, Wei Wang, Chongsheng Zhang, Weiping Ding, Bin Wang, Yaguan Qian, Zhen Han, Chunhua Su. Neighbor-enhanced Representation Learning for Link Prediction in Dynamic Heterogeneous Attributed Networks, ACM Transactions on Knowledge Discovery from Data (TKDD), 18 (8), 2024 (CCF B)

[8]  Jianhao Fu, Xiang Ling, Yaguan QIAN, Changjiang Li, Tianyue Luo, Jingzheng Wu. “Towards Query-Efficient Decision-Based Adversarial Attacks Through Frequency Domain”, ICME2024,  Niagra Falls, Canada  (CCF B)

[7]  Zhang Junjian, Tan Hao, Wang Le, Qian Yaguan, Gu Zhaoquan. “Rethinking Multi-Spatial Information for Transferable Adversarial Attacks on Speaker Recognition”, CAAI Transactions on Intelligence Technology, 2024. DOI:10.1049/cit2.12295

[6]  Xiang Ling, Lingfei Wu, Jiangyu Zhang, Zhenqing Qu, Wei Deng, Xiang Chen, Yaguan Qian, Chunming Wu, Shouling Ji, Tianyue Luo, Jingzheng Wu, Yanjun Wu. Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art. Computers & Security (COSE), 128(2023):1-24, 2023. (CCF B)

[5]  Hao Tan, Junjian Zhang, Huan Zhang, Le Wang, Yaguan Qian, Zhaoquan Gu. “NRI-FGSM: An Efficient Transferable Adversarial Attack for Speaker Recognition Systems”, In Proc. of the 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH-22), Incheon, Korea, 2022.

[4] Bin Zhu, Zhaoquan Gu, Yaguan Qian, Francis Lau, Zhihong Tian. “Leveraging Transferability and Improved Beam Search in Textual Adversarial Attacks”, Neurocomputing, 2022, 500(2022):135-142.

[3]  Wujie Zhou, Lu Yu, Yaguan Qian, Weiwei Qiu, Yang Zhou, Ting Luo. “Deep blind quality evaluator for multiply distorted images based on monogenic binary coding”, Journal of Visual Communication and Image Representation, 2019, 60: 305-311.

[2]  Wujie Zhou, Shaohua Dong, Caie Xu, Yaguan Qian. “Edge-aware Guidance Fusion Network for RGB–thermal Scene Parsing”, In Proc. of the 36th AAAI Conference on Artificial Intelligence (AAAI-22), Columbia, Canada, 2022. (CCF A)

[1]  Bin Zhu, Zhaoquan Gu, Yushun Xie, Danni Wu, Yaguan Qian, and Le Wang, “Word-Level Textual Adversarial Attack in the Embedding Space”, In Proc. of the International Joint Conference on Neural Networks (IJCNN-21), Shenzhen, China, 2021.

三、近五年主持的科研项目

[7] 国家自然科学基金，面上项目，面向视觉-语言预训练模型的多模态对抗迁移攻击（No.62476250），2025.1-2028.12.   项目负责人

[6] 浙江省自然科学基金，重点项目，对抗样本形成机理及其与深度神经网络的鲁棒性修复（No.LZ22F020007），2022.01-2024.12，项目负责人

[5] 浙江省自然科学基金，面上项目，基于机器学习的流量识别系统的安全性研究（No.LY17F020011），2017.01-2019.12，项目负责人

[4] 军委科技委国防科技创新特区项目，基于机器学习的XXXX预警研究（No.1916321TS00105711）， 2020.10-2021.06，项目负责人

[3] 浙江省多维感知技术应用与安全重点实验室开放基金项目（HIKKL-20230008），智能系统的对抗样本防御关键技术研究，2023.01-2023.12， 项目负责人

[2] 产教融合项目（海康威视），物联网边缘智能系统的安全技术研发，2020.11-2023.11，项目负责人

[1] 产教融合项目（杭州朗米科技），基于深度学习的复杂交通路口多目标跟踪与分类算法研究，2019.08-2020.06，项目负责人

四、获奖

[1] 基于物联网大数据的智慧农业共生系统的创新与实践, 中国发明协会2022年度发明创业奖创新奖, 二等奖（2/6）.

[2] 大数据智慧农业关键技术及在现代生态农业中的应用, 2022年度中国产学研合作促进会产学研合作创新与促进奖, 优秀奖（2/10）.

[3] 多维协同的智能物联网安全检测关键技术及应用, 2022年中国通信学会科技进步二等奖（5/14）.

五、授权发明专利

[7] 一种开放空间中行人换装再识别方法. 授权专利号：ZL202011423457.5

[6]基于深度学习的对抗样本攻击检测方法、装置及电子设备. 授权专利号：ZL202210630379.9

[5] 一种复杂交通路口的智能流量识别与统计方法. 授权专利号：ZL202010478988.8

[4] 一种基于Bayes-Stackelberg博弈的边缘智能移动目标防御方法. 授权专利号：ZL202010966915.3

[3] 一种不可察觉的对抗补丁生成方法. 授权专利号：ZL202011246415.9

[2] 一种深度神经网络的虚拟对抗训练方法、装置及设备.  授权专利号：ZL202110352167.4

[1] 基于注意力去噪的对抗样本防御方法、装置和系统. 授权专利号：ZL202110762352.0