Latest Updates
2024-11-05: Complete and submit the paper "Region-Guided Attack on the Segment Anything Model (SAM)".
2024-08-20: "RADAP: A Robust and Adaptive Defense Against Diverse Adversarial Patches on Face Recognition" accepted by *Pattern Recognition*.
2024-06-20: Successfully graduated with a PhD.
2024-05-23: Successfully passed the PhD dissertation defense.
2024-03-31: Updated the paper link.
Education
2018.09 - 2024.06 Nanjing University, Ph.D. in Computer Science and Technology, Member of RINC Group, Supervisor: Prof. Furao Shen
2016.09 - 2018.07 Nanjing University, M.S. in Computer Science and Technology, Member of RINC Group, Supervisor: Prof. Furao Shen
2009.09 - 2014.07 Fujian University of Technology, B.S. in Communication Engineering
Research Interests
- AI (Neural Network) Security
- Adversarial Machine Learning
- Computer Vision
- Deep Neural Networks
Research Achievements
Published Papers:
- Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie. RADAP: A Robust and Adaptive Defense Against Diverse Adversarial Patches on Face Recognition[J]. Pattern Recognition (2024): 110915. [Paper] (CCF-B,SCI,JCR-Q1)
- Xiaoliang Liu, Furao Shen, Jian Zhao and Changhai Nie. EAP: An effective black-box impersonation adversarial patch attack method on face recognition in the physical world[J]. Neurocomputing, 2024: 127517. [Paper] (CCF-C,SCI,JCR-Q2)
- Xiaoliang Liu, Furao Shen, Jian Zhao and Changhai Nie. Self-supervised learning of monocular 3D geometry understanding with two-and three-view geometric constraints[J]. The Visual Computer, 2024, 40(2): 1193-1204. [Paper] (CCF-C,SCI,JCR-Q2)
- Xiaoliang Liu, Furao Shen, Jian Zhao and Changhai Nie. RandoMix: a mixed sample data augmentation method with multiple mixed modes[J]. Multimedia Tools and Applications, 2024: 1-17. [Paper] (CCF-C,SCI,JCR-Q2)
- Xiaoliang Liu, Furao Shen, Jian Zhao and Changhai Nie. AugRmixAT: A data processing and training method for improving multiple robustness and generalization performance [C]. IEEE International Conference on Multimedia and Expo (ICME). 2022: 1-6. [Paper] (CCF-B,EI)
Submitted Papers:
- Xiaoliang Liu, Furao Shen, Feng Han, Jian Zhao and Changhai Nie. NeRFTAP: Enhancing transferability of adversarial patches on face recognition using neural radiance fields[J]. arXiv preprint arXiv:2311.17332, 2023. [Paper] (SCI,Under Review)
- Xiaoliang Liu, Furao Shen and Jian Zhao. Region-Guided Attack on the Segment Anything Model (SAM)[J]. arXiv preprint arXiv:2411.02974, 2024. [Paper] (SCI,Submitted to Journal)
Patents:
- Furao Shen, Kepan Gao, Xiaoliang Liu, et al. A method for indoor localization by fusing UWB and LiDAR: 202011520518[P] [2024-02-28].
Book Chapters:
- Furao Shen. Self-Organizing Incremental Learning Neural Networks[M]. Electronic Industry Press, September 2023. (Chapter 1: Mathematical Foundations)
Awards
2022.08 - 2023.03, the First Greater Bay Area (Huangpu) International Algorithm Competition, Adversarial Robustness Defense Algorithm for Deep Learning Models, Finalist Prize. (Individual Participation)
Research Projects
State Grid Corporation of China Headquarters Science and Technology Project, Research and Application of Substation HD Video and Robot Joint Inspection Technology Based on Multi-Dimensional Image Intelligent Matching and Recognition, Project Number: 520950200009. (Participant)
Ministry of Science and Technology Major Project - the STI 2030-Major Projects of China, Efficient Learning Mechanism of Spiking Networks Based on Neural Plasticity and Brain-Inspired Intelligence System, Grant Nos: 2021ZD0201300. (Participant)
National Natural Science Foundation of China General Program, Research on Novel Neural Networks for Incremental Unsupervised Learning, Grant Nos: 62276127. (Participant)
Research Services
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT, Peer Reviewer)
Other Information