导师个人简介：

刘博，女，副教授（高级工程师）、硕士生导师。2020年毕业于华中科技大学计算机系统结构专业，获工学博士学位。主要研究方向人工智能加速架构、GPU/FPGA/ASIC软硬件协同设计、人工智能系统安全。参与国家重点研发计划、主持国家自然科学基金项目，获国家发明专利4项，发表SCI/EI论文10余篇。获2025年度郑州市优秀青年科技人才称号。获2025年度IEEE HITC青年学者奖。

代表性科研项目：

1.国家自然科学基金青年项目，工业边缘智能检测领域的多模态数据统一表示学习方法研究，2025.01-2027.12，主持

2.武汉光电国家研究中心开放基金课题，面向多模态大模型的忆阻器存算芯片可靠性保障技术研究，2025.01-2027.12，主持

3.国家重点研发计划（课题），分布式高性能元数据组织模式与关键技术，2023.12-2026.11，参与

4.国家自然科学基金面上项目，以图为中心的多源异构大数据处理方法与技术研究，2024.01-2027.12，参与

代表性论文著作：

[1]Bo Liu, Yingnan Guo, Shun Wang, Shaofeng Zhao, Haokun Zheng, Haojie Huang, Jing Yang, Yuan Gao, Xiaokang Wang, Zhigao Zheng. One Modality is Enough: Multi-Modal Backdoor Attacks via Prototype-based Modality Rebalancing and Data Selection, IEEE Transactions on Consumer Electronics, 2026（SCI 1区TOP期刊）

[2]Bo Liu, Yingnan Guo, Xiang Chen, Shaofeng Zhao, Jubin Liu, Hui Xu. A Cloud-Edge-aided Processing-in-Memory Reliability Method for Cyber-Physical-Social Intelligence, Tsinghua Science and Technology, 2025（SCI 2区）

[3]Jiaxing Chen, Bo Liu, Shaofeng Zhao, Zhanbo Li, Hui Xu. Erasing Backdoor of Deep Neural Networks Using Neural Perturbation-based Attention Distillation. International Journal of Modeling, Simulation, and Scientific Computing (IJMSSC 2025),（ESCI）

[4]Xiang Chen, Bo Liu (通信作者), Shaofeng Zhao, Ming Liu, Hui Xu, Zhanbo Li, Zhigao Zheng. ICT: Invisible Computable Trigger Backdoor Attacks in Transfer Learning. IEEE Transactions on Consumer Electronics (IEEE TCE), 2024: 70(4), 6747-6758. （SCI，中科院二区，影响因子4.3）

[5]Shaofeng Zhao, Fang Wang, Bo Liu (通信作者), Dan Feng, Yang Liu. LayCO: Achieving Least Lossy Accuracy for Most Efficient RRAM-Based Deep Neural Network Accelerator via Layer-Centric Co-Optimization, Journal of Computer Science and Technology, 2023, 38, 328–347 (SCI 检索， CCF B 类期刊)

[6]Shaofeng Zhao, Bo Liu (通信作者), Fang Wang, Dan Feng, Xiang Chen. TOSA: Tolerating Stuck-At-Faults in Edge-Based RRAM Inference Accelerators, In Proceedings of the 29th IEEE International Conference on Parallel and Distributed Systems (ICPADS’23). IEEE, Hainan, China (CCF C 类会议)

[7]Bo Liu, Wenbin Jiang, Hai Jin, Xuanhua Shi, Yang Ma, Layrub: Layer-Centric Memory Reuse and Data Migration for Extreme-Scale Deep Learning Systems. In Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP’18). ACM, Vienna, Austria (CCF A 类会议)

[8]Hai Jin, Bo Liu, Wenbin Jiang, Yang Ma, Xuanhua Shi, Bingsheng He, Shaofeng Zhao. Layer-Centric Memory Reuse and Data Migration for Extreme-Scale Deep Learning on Many-Core Architectures. ACM Transactions on Architecture and Code Optimization, 2018, 15(3), 37:1-26 (SCI 检索， CCF A类期刊)

[9]Bo Liu, Wenbin Jiang, Shaofeng Zhao, Hai Jin, Bingsheng He. Gradient Sparsification and Accumulation for Low-Bandwidth Communication in Distributed Deep Learning. In Proceedings of the Green, Pervasive, and Cloud Computing (GPC’20). Springer, Xi’an, China (CCF C 类会议)

[10]Wenbin Jiang, Yang Ma, Bo Liu, Haikun Liu, Bingbing Zhou, Jian Zhu, Song Wu, Hai Jin. Layup: Layer-Adaptive and Multi-Type Intermediate-Oriented Memory Optimization for GPU-Based CNNs, ACM Transactions on Architecture and Code Optimization, 2019, 16(4), 39:1-23 (SCI 检索， CCF A 类期刊)

[11]Xuanhua Shi, Zhigao Zheng, Yongluan Zhou, Hai Jin, Ligang He, Bo Liu, Qiang Sheng Hua, Graph Processing on GPUs: A Survey. ACM Computing Surveys, 2018, 50(6), 81:1-35 (SCI 检索，影响因子 6.748)

招生信息：

课题组所属的省部级科研平台学术能力强大，科研经费充足，算力资源充裕！

欢迎对科创竞赛感兴趣的本科生加入！

欢迎对人工智能、计算机体系结构、操作系统等方向感兴趣的优秀学子报考研究生！

导师工作邮箱：liubo@zzu.edu.cn