Contact
- Office: No. 601, Room 339, Building 5
- Address: South Fourth Street 4#, Zhong Guan Cun, Beijing
- email:
lirj19###ios**ac*cn
About me
I am currently a Ph.D student in the group. My main research interests are:
- Adversarial Attack and Defence on Neural Networks
- Neural Network Verification
Education
- Sept. 2021 – present: Ph.D. Student in Computer Software and Theory at Institute of Software, Chinese Academy of Sciences and University of Chinese Academy of Sciences
- Sept. 2019 – Jun. 2021: Master Student in Computer Software and Theory at Institute of Software, Chinese Academy of Sciences and University of Chinese Academy of Sciences
- Sept. 2015 – Jun. 2019: Computer Science and Technology (Bachelor’s degree) at CS, Changzhou Institute of Technology
Publications
- ISS-Scenario: Scenario-based Testing in CARLA. In Theoretical Aspects of Software Engineering - 18th International Symposium, TASE 2024, Guiyang, China, July 29 - August 1, 2024, Proceedings, volume 14777 of Lecture Notes in Computer Science, pages 279-286, 2024. DOI BIB :
- Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors. In Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXVI, volume 15124 of Lecture Notes in Computer Science, pages 269-287, 2024. DOI BIB :
- Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds. In SETTA 2024 - Symposium on Dependable Software Engineering Theories, Tools and Applications, Lecture notes in Computer Science, 2024. BIB :
- Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning. In 44th IEEE/ACM 44th International Conference on Software Engineering, ICSE 2022, Pittsburgh, PA, USA, May 25-27, 2022, pages 2189-2201, 2022. DOI BIB :
- Reach-avoid Analysis for Stochastic Discrete-time Systems. In 2021 American Control Conference, ACC 2021, New Orleans, LA, USA, May 25-28, 2021, pages 4879-4885, 2021. DOI BIB :
- Enhancing Robustness Verification for Deep Neural Networks via Symbolic Propagation. In Formal Aspects Comput. 33(3):407-435, 2021. DOI BIB :
- Improving Neural Network Verification through Spurious Region Guided Refinement. In Tools and Algorithms for the Construction and Analysis of Systems - 27th International Conference, TACAS 2021, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2021, Luxembourg City, Luxembourg, March 27 - April 1, 2021, Proceedings, Part I, volume 12651 of Lecture Notes in Computer Science, pages 389-408, 2021. DOI BIB :
- PRODeep: a platform for robustness verification of deep neural networks. In ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, Virtual Event, USA, November 8-13, 2020, pages 1630-1634, 2020. DOI BIB :