Chen GONG ( 龚晨 )
Ph.D. Student

Department of Computer Science, University of Virginia

Location: Charlottesville, VA, USA
Short Bio | Education | Research Experiences | Publications | Awards & Honors | Services

Email: fzv6en@virginia.edu
[CV] [Google scholar] [Github] [Zhihu]

News

Short Bio

 From 2020.06 - 2023.06,I am a master's student in the Institute of Automation, Chinese Academy of Sciences, supervised by Prof. Xinwen HOU. From 2021.09 - 2022.09, I worked as a visiting student in the School of Computing and Information Systems, Singapore Management University, where I was honored to work closely with Prof. David Lo, Zhou Yang and Jieke Shi. In 2020.06, I obtained my Bachelor's degree from the School of Information Engineering, China University of Geosciences, Beijing, where I worked with Prof. Yunyun Niu. Currently, I focus on the following research topics: reinforcement learning security; offline reinforcement learning; convex duality in reinforcement learning; adversarial policy; generative model; variational inference.

Education

Selected research experiences
  • 2021.08-2022.09, School of Computing and Information Systems, Singapore Management University, Singapore, Supervisor: Prof. David Lo | Adversarial Policy & Reinforcement Learning Testing
  • 2021.02-Now, Institute of Automation, Chinese Academy of Sciences, Beijing, China, Supervisor: Prof. Xinwen HOU | Offline Reinforcement learning, Off-policy evaluation, Convex duality & Generative model
  • 2019.11-2020.12, Institute of Automation, Chinese Academy of Sciences, Beijing, China, Supervisor: Prof. Xinwen HOU | Reinforcement learning & Variational inference
  • 2017.12-2019.02, China University of Geosciences, Beijing, China, Supervisor: Prof. Yunyun Niu | Machine learning in medicine

Publications

 "*" means equal contribution.
2024

  • Kecen Li*, Chen Gong*, Zhixiang Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang. “PRIVIMAGE: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining”, 33rd USENIX Security Symposium (USENIX Security), 2024. [Acceptance Rate: ???] [Supervised the project] [Arxiv] [Project Page] [Code]

  • Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang. “BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets”, 45th IEEE Symposium on Security and Privacy (IEEE S&P), 2024. [Acceptance Rate in Cycle 3: 70/601=11.6%] [Arxiv] [Code]

  • Siyu Xing, Chen Gong, Hewei Guo, Xiaoyu Zhang, Xinwen Hou, Yu Liu. “GAN Inversion for Image Editing via Unsupervised Domain Adaptation”, IEEE International Conference on Multimedia and Expo (ICME), 2024. [Acceptance Rate: 31.0%] [Supervised the project] (To appear)

  • Xianjie Zhang, Jiahao Sun, Chen Gong, Kai Wang, Yifei Cao, Hao Chen and Yu Liu, “Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling”, International Joint Conference on Autonomous Agents and Multi-agent Systems (AAMAS), 2024. [Paper]

2023

  • Chao Li, Chen Gong, Qiang He, Xinwen Hou, “Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control”, 37th Conference on Neural Information Processing Systems (NeurIPS), 2023. [Supervised the project] [Paper]

  • Bowen Xu, Thanh-Dat Nguyen, Thanh Le-Cong, Thong Hoang, Jiakun Liu, Kisub Kim, Chen Gong, Changan Niu, Chenyu Wang, Bach Le, David Lo, “Are We Ready to Embrace Generative AI for Software Q&A?”, 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), NIER track, 2023. [Paper] [Code]

  • Chao Li*, Chen Gong*, Qiang He, Xinwen Hou, Yu Liu, “Centralized Cooperative Exploration Policy for Continuous Control Tasks”, International Joint Conference on Autonomous Agents and Multi-agent Systems (AAMAS), 2023. [Supervised the project] [Paper] [Code]

2022

  • Chen Gong, Zhou Yang, Yunpeng Bai, Jieke Shi, Arunesh Sinha, Bowen Xu, David Lo, Xinwen Hou, Guoliang Fan, “Curiosity-Driven and Victim-Aware Adversarial Policies”, Annual Computer Security Applications Conference (ACSAC), 2022. (Technical Track, 15 pages) [Paper] [Code] [Slides] (Artifacts Evaluation: Functional) (Won Honorable Mention Award!)

  • Qiang He, Huangyuan Su, Chen Gong, Xinwen Hou, “MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning”, Decision Awareness in Reinforcement Learning Workshop at ICML, 2022. (Poster, 11 pages) [Arxiv]

  • Yunpeng Bai*, Chen Gong*, Bin Zhang, Guoliang Fan, Xinwen Hou, Yu Liu. “Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution”, International Joint Conference on Neural Networks (IJCNN), 2022. (Oral, 10 pages) [Paper] [Code]

2021

  • Chen Gong*, Qiang He*, Yunpeng Bai, Xinwen Hou, Guoliang Fan, Yu Liu “Wide-Sense Stationary Policy Optimization with Bellman Residual on Video Games”, IEEE International Conference on Multimedia and Expo (ICME), 2021: 1-6. (Oral, 6 pages) [Paper]

  • Chen Gong, Yunpeng Bai, Xinwen Hou, Xiaohui Ji. “Stable Training of Bellman Error in Reinforcement Learning”, International Conference on Neural Information Processing (ICONIP), 2020:439-448. (Oral, 10 pages) [Paper]

  • Chen Gong, Xinchen Zhou, Yunyun Niu. “Pattern recognition of epilepsy using parallel probabilistic neural network”, Applied Intelligence, 2021: 1-12. (IF=5.09) [Paper]

  • Chen Gong, Jiahui Liu, Yunyun Niu. “Intracranial Epileptic Seizures Detection Based on an Optimized Neural Network Classifier”, Chinese Journal of Electronics, 2021, 30(3): 419-425. (IF=1.01) [Paper]

2020
  • Chen Gong, Xiaoxiong Zhang, Yunun Niu. “Identification of epilepsy from intracranial EEG signals by using different neural network models”, Computational Biology and Chemistry, 2020, 87: 107310. (IF=3.78) [Paper]
Pre-print

  • Hao Chen, Chen Gong*, Yize Wang, Xinwen Hou. “Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning”. under review IEEE Conference on Decision and Control (CDC). [Arxiv] [Code]

  • Chen Gong*, Qiang He*, Yunpeng Bai*, Zhou Yang, Xiaoyu Chen, Xinwen Hou, Xianjie Zhang, Yu Liu, Guoliang Fan. “The f-Divergence Reinforcement Learning Framework”. [Arxiv]

  • Xiaoyu Chen*, Chen Gong*, Qiang He, Xinwen Hou, Yu Liu, “LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders”. [Arxiv]

Student Supervision

 I'm hourned to (co-)supervise the following students:
  • Kecen Li, a Master Student at CASIA, working on differential private images synthesis, publication: USENIX Security 2024, S&P 2024.

Awards & Honors

Awards:

  • 2022, the 19th China Post-graduate Mathematical Contest in Modeling, Second Prize
  • 2020, the COMAP's Mathematical Contest in Modeling, Finalist
  • 2019, the COMAP's Mathematical Contest in Modeling, Meritorious Winner
  • 2018, the COMAP's Mathematical Contest in Modeling, Honorable Mention
  • 2018, the Contemporary Undergraduate Mathematical Contest in Modeling, First prize in Beijing
  • 2017, the Mathematics Competition of China University of Geosciences, First prize

Honors:

  • 2021, University of Chinese Academy of Sciences, Merit Student
  • 2020, Beijing Municipal Education Commission, Beijing Outstanding Graduates
  • 2020, China University Of Geosciences, Beijing, School-level Excellent Graduation Thesis
  • 2017, China University Of Geosciences, Beijing, Outstanding Member
  • 2017, Ministry of Education of the people's Republic of China, National Scholarship for Undergraduates

Services
  • 2024, ICME PC Member, CCS Shadow Reviewer, CDC Reviewer
  • 2023, CDC Reviewer
  • 2022, ACSAC Artifacts Evaluation Committee
  • IEEE Transactions on Industrial Electronics Reviewer
  • ACM Transactions on Intelligent Systems and Technology Reviewer