个人简介：

吴炜滨，beat365唯一官方网站副教授，中国计算机学会软件工程专业委员会执行委员。2021年于香港中文大学计算机科学与工程学系获得博士学位，2017年于同济大学电子与信息工程学院获得学士学位。主要研究方向包括可信人工智能、深度学习、计算机视觉、自然语言处理、智能软件工程等，重点关注深度学习（智能软件）的可靠性、安全性、可解释性与隐私性。主持国家自然科学基金项目、招联校企合作项目等多个科研项目。为多个国际顶级会议和期刊的审稿人，如ICML、ICLR、ICCV、ECCV、ACL、EMNLP、TPAMI等。近年来在NeurIPS、CVPR、FSE等人工智能、计算机视觉、软件工程领域的CCF A类国际顶级会议上发表论文18篇。

 

招生信息：

每年招收推免或统考的硕士研究生。招生方向包括但不限于：可信人工智能（Trustworthy Artificial Intelligence）、深度学习（Deep Learning）、计算机视觉（Computer Vision）、自然语言处理（Natural Language Processing）、智能软件工程（Intelligent Software Engineering）等。

欢迎有意向攻读研究生的同学，以及学有余力且有志于参与科研的低年级本科生同学与我联系。

 

课题组快讯：

  • 热烈祝贺课题组的本科生吴翰、区冠彦同学的学术论文被人工智能领域的CCF A类国际顶会CVPR 2024接收！
  • 热烈祝贺课题组的本科生邓阳同学在大三年级首次投稿的学术论文被人工智能领域的CCF A类国际顶会NeurIPS 2023接收！

 

课题组学生去向：

  • 美国普渡大学：区同学（全奖直博）
  • 瑞典查尔姆斯理工大学：吴同学（硕士，Avancez Scholarship）
  • 香港城市大学：李同学（硕士）
  • 北京大学：邓同学（硕士）

 

邮箱：

image-20240727105012-1@mail.sysu.edu.cn

 

教学活动：

SSE219           计算机组成原理                本科生专业必修课

SSE207           计算机组成原理实验         本科生专业必修课

SSE5203         软件分析及质量保证         研究生专业必修课

SSE5726         可信人工智能                   研究生专业必修课

 

获奖荣誉：

Outstanding Reviewer, ICCV, 2023

Talent Development Scholarship, Hong Kong, 2018

本科生国家奖学金, China, 2016, 2015, 2014

 

学术服务：

Session Chair：Causality and Explainable AI (ICONIP 2020)

会议期刊审稿人：

NeurIPS（CCF A类），AAAI（CCF A类），CVPR（CCF A类），ICCV（CCF A类），ACL（CCF A类）；

TPAMI（中科院一区），TNNLS（中科院一区），TIP（中科院一区），TKDE（CCF A类）

 

主要科研项目：

2023 - 2025：（主持）国家自然科学基金青年科学基金项目

2024 - 2027：（主持）招联校企合作项目

 

代表性学术成果：

[FSE 25] W. Wu, H. Hu, Z. Fan, Y. Qiao, Y. Huang, Y. Li, Z. Zheng, M. R. Lyu, "An Empirical Study of Code Clones from Commercial AI Code Generators," ACM International Conference on the Foundations of Software Engineering, 2025. (CCF A类会议)

[FSE 25] W. Wu, Y. Cao, N. Yi, R. Ou, Z. Zheng, "Detecting and Reducing the Factual Hallucinations of Large Language Models with Metamorphic Testing," ACM International Conference on the Foundations of Software Engineering, 2025. (CCF A类会议)

[FSE 24] Y. Huang, Y. Li, W. Wu (通讯作者), J. Zhang, M. R. Lyu, "Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials," ACM International Conference on the Foundations of Software Engineering, 2024. (CCF A类会议)

[CVPR 24] H. Wu*, G. Ou*, W. Wu (通讯作者), Z. Zheng, "Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024. (CCF A类会议)

[AAAI 24] J. Zhang, Y. Huang, Z. Xu, W. Wu (通讯作者), M. R. Lyu, "Improving the Adversarial Transferability of Vision Transformers with Virtual Dense Connection," AAAI Conference on Artificial Intelligence, 2024. (CCF A类会议)

[AAAI 24] J. Zhang, W. Gu, Y. Huang, Z. Jiang, W. Wu (通讯作者), M. R. Lyu, "Curvature-Invariant Adversarial Attacks for 3D Point Clouds," AAAI Conference on Artificial Intelligence, 2024. (CCF A类会议)

[NeurIPS 23] Y. Deng, W. Wu (通讯作者), J. Zhang, Z. Zheng, "Blurred-Dilated Method for Adversarial Attacks," Conference on Neural Information Processing Systems, 2023. (CCF A类会议)

[IJCAI 23] J. Zhang, Y. Huang, W. Wu (通讯作者), M. R. Lyu, "Towards Semantics- and Domain-Aware Adversarial Attacks," International Joint Conference on Artificial Intelligence, 2023. (CCF A类会议)

[ISSTA 23] W. Wang, J. Huang, C. Chen, J. Gu, J. Zhang, W. Wu, P. He, M. R. Lyu, "Validating Multimedia Content Moderation Software via Semantic Fusion," ACM SIGSOFT International Symposium on Software Testing and Analysis, 2023. (CCF A类会议)

[CVPR 23] J. Zhang, Y. Huang, W. Wu (通讯作者), M. R. Lyu, "Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. (CCF A类会议)

[CVPR 23] J. Zhang, J.-T. Huang, W. Wang, Y. Li, W. Wu (通讯作者), X. Wang, Y. Su, M. R. Lyu, "Improving the Transferability of Adversarial Samples by Path-Augmented Method," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. (CCF A类会议)

[ICSE 23] W. Wu, J. Zhang, V. J. Wei, X. Chen, Z. Zheng, I. King, and M. R. Lyu, "Practical and Efficient Model Extraction of Sentiment Analysis APIs," IEEE/ACM International Conference on Software Engineering, 2023. (CCF A类会议)

[ICSE 23] W. Wang, J.-T. Huang, W. Wu, J. Zhang, Y. Huang, S. Li, P. He, and M. R. Lyu, "MTTM: Metamorphic Testing for Textual Content Moderation Software," IEEE/ACM International Conference on Software Engineering, 2023. (CCF A类会议)

[AAAI 23] Z. Li, W. Wu, Y. Su, Z. Zheng, and M. R. Lyu, "CDTA: A Cross-Domain Transfer-Based Attack with Contrastive Learning," AAAI Conference on Artificial Intelligence, 2023. (CCF A类会议, Oral Presentation)

[CVPR 22] J. Zhang, W. Wu (通讯作者), J.-T. Huang, Y. Huang, W. Wang, Y. Su, and M. R. Lyu, "Improving Adversarial Transferability via Neuron Attribution-Based Attacks," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022. (CCF A类会议)

[CVPR 21] W. Wu, Y. Su, M. R. Lyu, and I. King, "Improving the Transferability of Adversarial Samples with Adversarial Transformations," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021. (CCF A类会议)

[CVPR 20] W. Wu, Y. Su, X. Chen, S. Zhao, I. King, M. R. Lyu, and Y. W. Tai, "Boosting the Transferability of Adversarial Samples via Attention," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. (CCF A类会议)

[CVPR 20] W. Wu, Y. Su, X. Chen, S. Zhao, I. King, M. R. Lyu, and Y. W. Tai, "Towards Global Explanations of Convolutional Neural Networks with Concept Attribution," IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. (CCF A类会议, Oral Presentation)

[DSN 19] W. Wu, H. Xu, S. Zhong, M. R. Lyu, and I. King, "Deep Validation: Toward Detecting Real-World Corner Cases for Deep Neural Networks," IEEE/IFIP International Conference on Dependable Systems and Networks, 2019. (CCF B类会议)

[DSN-W 19] H. Xu, Z. Chen, W. Wu, Z. Jin, S.-Y. Kuo, and M. R. Lyu, "NV-DNN: Towards Fault-Tolerant DNN Systems with N-Version Programming," IEEE/IFIP International Conference on Dependable Systems and Networks Workshops, 2019. (EI)