»姓名：杨兴浩 | »系属：自动化系 |
|
»学位：博士 | »职称：副教授 | |
»专业：模式识别与智能系统 | »导师类别：硕士生导师 | |
»电子邮箱：yangxh@upc.edu.cn | ||
»联系电话：- | ||
»通讯地址：山东省青岛市黄岛区长江西路66号 | ||
»概况：https://xinghaoyang.github.io/ | ||
◎研究方向 主要研究方向为自然语言处理与人工智能安全，聚焦大模型及智能系统的攻防机理与鲁棒性防护，具体涵盖大模型越狱攻防、文本对抗攻防、文本后门攻防、多模态模型安全、大推理模型与RAG智能系统安全等研究领域。 最新研究成果见个人主页：https://xinghaoyang.github.io/ ◎教育经历 2018.08-2022.04，悉尼科技大学，计算机科学，博士学位 2015.09-2018.06，中国石油大学（华东），信息与通信工程，硕士学位 2011.09-2015.06，中国石油大学（华东），电子信息工程，学士学位 ◎工作经历 2022年04月-至今，中国石油大学（华东），控制科学与工程学院，副教授 ◎学术兼职 1.山东省人工智能学会理事 2.SCI期刊NPL副编辑 3.IEEE SMC协会感知计算技术委员会会员 4.中国计算机学会（CCF）专业会员 5.中国图象图形学学会-机器视觉专业委员会委员 ◎主讲课程 1.《数字图像处理》 2.《图像处理与计算机视觉》 ◎指导研究生及博士后 1. 毕业研究生11人，其中5人在中国人民大学、上海交通大学等高校读博，6人参加工作。 2. 在读研究生7人。 3. 学生获奖情况：研究生国家奖学金（李晨）、校级优秀硕士论文（齐宇鹏）、ICNLP2026最佳论文奖（汪佳玮） ◎承担项目 1. 国家自然科学青年基金项目, 基于单调弱次模优化的有界文本攻击方法研究, 62406341, 2025-01 至 2027-12, 30万元, 主持 2. 山东省自然科学基金-优秀青年科学基金项目（海外）, 基于数据模型耦合的鲁棒表示学习方法研究, 2023HWYQ-070, 2023-01 至 2025-12, 60万元, 主持 3. 山东省自然科学基金-青年基金项目, 基于对抗性攻击与防御的鲁棒文本数据表示方法研究, ZR2023QF051, 2024-01 至 2026-12, 15万元, 主持 4. 山东省创新团队及人才计划类项目, 山东省青年科技人才托举项目资助经费, ZX20240304, 2024-11 至 2026-10, 5万元, 主持（同年全校仅两人入选） 5. 自主创新科研计划项目（理工科）-青年基金，基于多变量组合优化的文本对抗性研究，22CX06059A，2022-09 至 2025-04，18万元，主持 6. 山东省自然科学基金【重大基础研究项目】, 基于工业互联网的离散制造业生产安全智能化关键技术研究, ZR2023ZD32, 2024-01 至 2026-12, 160万元，参与 7. 青岛市自然科学基金【重点项目】, 基于跨模态VLA模型的具身智能算法研究及应用, 25-3-1-3-zyyd-jch, 2025-12 至 2028.11, 300万元，参与 8. 井下视像测井图像智能化处理方法研究, HX20241100, 2024-11 至 2025-12, 32万元，参与 9. 多视角稀疏编码融合深度学习的页岩油气甜点识别, HX20220988, 2022-10 至 2024-10, 23万元，参与 10. 固体推进剂细观燃烧数值模拟的降阶方法研究, HX20240502, 2024-1 至 2025-12, 30万元，参与 ◎获奖情况 1. 2022年，山东省人工智能学会自然科学奖一等奖 2. 2022年，中国自动化学会自然科学奖二等奖 3. 2021年，青岛市大数据优秀学术成果奖 4. 2021年，澳大利亚悉尼科技大学副校长会议基金 ◎荣誉称号 1. 山东省优青 2. 山东省青托 ◎著作 [1] Aneesh Sreevallabh Chivukula, Xinghao Yang, Bo Liu, Wei Liu, Wanlei Zhou. Adversarial machine learning: attack surfaces, defence mechanisms, learning theories in artificial intelligence. Springer Nature. DOI: https://doi.org/10.1007/978-3-030-99772-4, 2023. ◎论文 Selected Conference Papers [1] Mingze Ni, Yongshun Gong, Xinghao Yang, and Wei Liu. Is LoRA Robust to Adversarial Attacks? Expectation-Based Regularization for Parameter-Efficient Adversarial Training. In Findings of the Association for Computational Linguistics: EMNLP 2026., October 24-29, 2026, Budapest, Hungary. [2] Ao Wang, Xinghao Yang, Yongshun Gong, Wei Liu, Baodi Liu and Weifeng Liu. Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance. ACL 2026, July 2-7, 2026, San Diego. [3] Zikai Wang, Xinghao Yang, Bingfeng Zhang, and Weifeng Liu. Safety Anchor-Guided Adaptive Bias Decay for Jailbreak Defense. ICASSP 2026, May 4-8, 2026, Barcelona. [4] Jiawei Wang, Xinghao Yang, Baodi Liu and Weifeng Liu. Intermediate-Layer Filtering for Text Backdoor Defense. ICNLP 2026, March 20-22, 2026, Xi'an. Best Paper Award. [5] Yidan Xu, Xinghao Yang, Wei Liu, Bao-di Liu, Weifeng Liu. Disentangled Information Bottleneck for Adversarial Text Defense. EMNLP 2025, November 4-9, 2025, Suzhou. [6] Ao Wang, Xinghao Yang, Chen Li, Bao-di Liu, Weifeng Liu. Adaptive Immune-based Sound-Shape code Substitution for Adversarial Chinese Text Attacks. EMNLP 2024, November 12-16, 2024, Miami. [7] Chen Li, Xinghao Yang, Baodi Liu, Weifeng Liu, Honglong Chen. Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation. IJCAI 2023, August 19-25, 2023, Macao. [8] Xinghao Yang, Weifeng Liu, Dacheng Tao, Wei Liu. BESA: BERT-based Simulated Annealing for Adversarial Text Attacks. The 30th International Joint Conference on Artificial Intelligence (IJCAI 2021). August 21-26, 2021, Virtual Conference. [9] Changwei Sung, Xinghao Yang, Chungshou Liao, and Wei Liu. IntRoute: An Integer Programming based Approach for Best Bus Route Discovery. The 26th International Conference on Database Systems for Advanced Applications (DASFAA 2021). April 11-14, 2021, Virtual Conference. [10] Xinghao Yang, Weifeng Liu, James Bailey, Dacheng Tao, and Wei Liu. Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic Search. The 35th AAAI Conference on Artificial Intelligence (AAAI 2021). February 2-9, 2021, Virtual Conference. [11] Xinghao Yang and Wei Liu. Population Location and Movement Estimation through Cross-domain Data Analysis. The 29th International Joint Conference on Artificial Intelligence (IJCAI 2020). January 7-15, 2021, Virtual Conference. [12] Xinghao Yang, and Wei Liu. Cyber Attack to AI Systems: Targeted Attention-based Attacks to Road Sign Recognition Models. In Proceedings of the 2020 Cyber Defence Next Generation Technology Conference (CDNG 2020). [13] Aneesh Chivukula, Xinghao Yang, and Wei Liu: Adversarial Deep Learning with Stackelberg Games. The 26th International Conference on Neural Information Processing (ICONIP 2019). December 12-15, 2019, Sydney, Australia. [14] Sichao Fu, Xinghao Yang, Weifeng Liu. The Comparison of Different Graph Convolutional Neural Networks for Image Recognition. The 10th International Conference on Internet Multimedia Computing and Service (ICIMCS 2018). August 17-19, 2018, Nanjing, China. [15] Xinghao Yang, Weifeng Liu. Multiple Scale Canonical Correlation Analysis Networks for Two-view Object Recognition. The 24th International Conference on Neural Information Processing (ICONIP 2017). November 14-18, 2017, Guangzhou, China. [16] Xinghao Yang, Hongli Liu, Weifeng Liu, ZhengJun Zha. Sparse Principle Motion Component for One-shot Gesture Recognition. The 7th International Conference on Internet Multimedia Computing and Service (ICIMCS 2015). August 19-21, 2015, Zhangjiajie, China. Selected Journal Papers [1] Puhua Jia, Xinghao Yang, Yongwei Tang, Baodi Liu, Wei Li and Weifeng Liu. Universal Attack based Focal Enhancement for Bearing Fault Diagnosis. Knowledge-Based Systems, 2026, 348: 116344. [2] Chen Li, Xinghao Yang, Ao Wang, Yongshun Gong, Baodi Liu and Weifeng Liu. Multiobjective Simulated Annealing-Based Stopwords Substitution for Rubbish Text Attack. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2026. [3] Yang An, Zhibin Li, Xiaoyu Li, Wei Liu, Xinghao Yang, Haoliang Sun, Meng Chen, Yu Zheng, Yongshun Gong. Spatio-Temporal Multivariate Probabilistic Modeling for Traffic Prediction. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025, 37: 2986-3000. [4] Jian Pang, Weifeng Liu, Bingfeng Zhang, Xinghao Yang, Baodi Liu, Dapeng Tao. MCNet: Magnitude consistency network for domain adaptive object detection under inclement environments. Pattern Recognition, 2024, 145: 109947. [5] Renjie Xu, Xinghao Yang, Xingxing Yao, Dapeng Tao, Weijia Cao, Xiaoping Lu, Weifeng Liu. Self-Paced Hard Task-Example Mining for Few-Shot Classification. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023, 33: 5631-5644. [6] Xinghao Yang, Yongshun Gong, Weifeng Liu, James Bailey, Dacheng Tao, Wei Liu. Semantic-Preserving Adversarial Text Attacks. IEEE Transactions on Sustainable Computing (TSUSC), 2023, 8: 583-595. [7] Xinghao Yang, Yupeng Qi, Honglong Chen, Baodi Liu, Weifeng Liu. Generation-based parallel particle swarm optimization for adversarial text attacks. Information Sciences, 2023, 644: 119237. [8] Xinghao Yang, Weifeng Liu, Wei Liu. Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022, 34: 2948-2961. [9] Xinghao Yang, Weifeng Liu, Shengli Zhang, Wei Liu, Dacheng Tao. Targeted Attention Attack on Deep Learning Models in Road Sign Recognition. IEEE Internet of Things Journal (IoT-J), 2021, 8:4980-4990. [10] Aneesh Chivukula, Xinghao Yang, Tianqing Zhu, Wanlei Zhou, and Wei Liu. Game Theoretical Adversarial Deep Learning with Variational Adversaries. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021, 33: 3568-3581. [11] Xinghao Yang, Weifeng Liu, Wei Liu, Dacheng Tao. A Survey on Canonical Correlation Analysis. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021, 33: 2349-2368. ESI highly cited [12] Weifeng Liu, Xinghao Yang, Dapeng Tao, Jun Cheng, Yuanyan Tang. Multiview dimension reduction via Hessian multiset canonical correlations. Information Fusion, Elsevier, 2018, 41: 119 - 128. ESI highly cited [13] Xinghao Yang, Weifeng Liu, Dapeng Tao, Jun Cheng, Shuying Li. Multiview Canonical Correlation Analysis Networks for Remote Sensing Image Recognition. IEEE Geoscience and Remote Sensing Letters (GRSL), 2017, 14: 1855-1859. [14] Xinghao Yang, Weifeng Liu, Dapeng Tao, Jun Cheng. Canonical Correlation Analysis Networks for Two-view Image Recognition. Information Sciences, Elsevier, 2017, 385: 338-352. ESI highly cited ◎专利 1.刘伟锋; 刘虹良; 杨兴浩; 基于语义一致性的抽象摘要文本防御方法，2024- 3-13，中国，ZL202410281941.0 2.刘伟锋; 贾普华; 杨兴浩; 一种针对故障诊断模型的通用对抗扰动生成方法, 2023-12-19, 中国, ZL202311243908.0 3.刘伟锋; 杨兴浩; 潘晓; 一种基于典型相关分析网络的二视角图像识别方法, 2019-5-14, 中国, ZL2 01610663936.1 4.刘伟锋; 杨兴浩; 一种基于多视角典型相关分析的人脸识别方法及其系统, 2019-4-12, 中国, ZL201 610055275.4 | ||
