Biography
I am a fourth-year Ph.D. student of TSAIL Group in the Department of Computer Science and Technology, Tsinghua University, advised by Prof. Jun Zhu. I also collaborate with Prof. Hang Su and Prof. Xiaolin Hu closely.
I was a visiting student from June, 2016 to September, 2016 in the Robotics Institute, Carnegie Mellon University, advised by Prof. Fernando De la Torre. I was a research intern in 2017 at Intel Labs China, collaborating with Dr. Jianguo Li. I was a research intern from July, 2018 to September, 2018 at Tencent AI Lab. I was an intern under the NVAIL program of NVIDIA from 2017 to 2020.
My research interest includes machine learning, deep learning and their applications in computer vision. Recently, I am interested in interpretability and robustness of deep learning.
My research is supported by Tsinghua Future PhD, MSRA, Baidu, ByteDance Fellowships.
Competitions
-
Our team (Xiao Yang, Dingcheng Yang, Shilong Liu, Zihao Xiao, Yinpeng Dong) won the first place in the GeekPwn DeepFake competition (October 24th, 2020).
-
Our team (Shuyu Cheng, Xiao Yang, Dingcheng Yang, Yinpeng Dong) won the first places in the GeekPwn CAAD CTF and Adversarial Patch competitions (October 24th, 2019).
-
Our team (Shuyu Cheng and Yinpeng Dong) won the second place in the Untargeted Attack track of NeurIPS 2018 Adversarial Vision Challenge.
-
Our team (Yinpeng Dong, Tianyu Pang, Chao Du) won the second places in the Targeted Adversarial Attack track and Defense Against Adversarial Attack track, as well as the third place in the Non-targeted Adversarial Attack track of GeekPwn CAAD (Competition on Adversarial Attacks and Defenses).
-
Our team (Tianyu Pang, Chao Du, Yinpeng Dong) won the first place in GeekPwn CAAD (Competition on Adversarial Attacks and Defenses) CTF competition (Las Vegas) in August 10th, 2018.
-
Our team (Yinpeng Dong, Fangzhou Liao, Tianyu Pang) won the first places in all three sub-competitions (Non-targeted Adversarial Attacks, Targeted Adversarial Attacks and Defense Against Adversarial Attack) of NeurIPS 2017 Adversarial Attacks and Defenses. We release our codes at [non-targeted attack], [targeted attack] and [defense] for these three tracks. The detailed algorithms are summarized in Boosting Adversarial Attacks with Momentum and Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser.
-
Our team (Yujie Qian, Yinpeng Dong, Ye Ma) won the the second place in KDDCUP 2016. This competition is about paper acceptance prediction.
Publications
-
Bag of Tricks for Adversarial Training
Tianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, and Jun Zhu
International Conference on Learning Representations (ICLR), Vienna, Austria, 2021
-
Adversarial Distributional Training for Robust Deep Learning
Yinpeng Dong*, Zhijie Deng*, Tianyu Pang, Hang Su, and Jun Zhu (* indicates equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2020
[arXiv]
[appendix]
[code]
[poster]
-
Understanding and Exploring the Network with Stochastic Architectures
Zhijie Deng, Yinpeng Dong, Shifeng Zhang, and Jun Zhu
Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2020
-
Boosting Adversarial Training with Hypersphere Embedding
Tianyu Pang, Xiao Yang, Yinpeng Dong, Kun Xu, Hang Su, and Jun Zhu
Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2020
-
Benchmarking Adversarial Robustness on Image Classification (Oral)
Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Zihao Xiao, and Jun Zhu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2020
[arXiv]
[appendix]
[code]
[video]
[slide]
-
Towards Privacy Protection by Generating Adversarial Identity Masks
Xiao Yang, Yinpeng Dong, Tianyu Pang, Jun Zhu, and Hang Su
arXiv preprint 2003.06814
-
Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, and Jun Zhu
International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020
-
Improving Black-box Adversarial Attacks with a Transfer-based Prior
Shuyu Cheng*, Yinpeng Dong*, Tianyu Pang, Hang Su, and Jun Zhu (* indicates equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2019
[arXiv]
[code]
-
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks (Oral)
Yinpeng Dong, Tianyu Pang, Hang Su, and Jun Zhu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019
[arXiv]
[code]
[video]
[poster]
-
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, and Jun Zhu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019
[arXiv]
[code]
[poster]
-
Stochastic Quantization for Learning Accurate Low-bit Deep Neural Networks
Yinpeng Dong, Renkun Ni, Jianguo Li, Yurong Chen, Hang Su, and Jun Zhu
International Journal of Computer Vision (IJCV), 2019
[code]
-
Batch Virtual Adversarial Training for Graph Convolutional Networks
Zhijie Deng, Yinpeng Dong, and Jun Zhu
ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Representation, Long Beach, USA, 2019
-
Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
Yinpeng Dong, Hang Su, Jun Zhu, Fan Bao, and Bo Zhang
AAAI-19 Workshop on Network Interpretability for Deep Learning, Honolulu, Hawaii, USA, 2019
-
Composite Binary Decomposition Networks
You Qiaoben, Zheng Wang, Jianguo Li, Yinpeng Dong, Yu-Gang Jiang, and Jun Zhu
The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), Honolulu, Hawaii, USA, 2019
-
Adversarial Vision Challenge
Wieland Brendel, Jonas Rauber, Alexey Kurakin, Nicolas Papernot, Behar Veliqi, Sharada P. Mohanty, Florian Laurent, Marcel Salathé, Matthias Bethge, Yaodong Yu, Hongyang Zhang, Susu Xu, Hongbao Zhang, Pengtao Xie, Eric P. Xing, Thomas Brunner, Frederik Diehl, Jérôme Rony, Luiz Gustavo Hafemann, Shuyu Cheng, Yinpeng Dong, Xuefei Ning, Wenshuo Li, Yu Wang
NeurIPS 2018 Competition Chapter
-
Towards Robust Detection of Adversarial Examples (Spotlight)
Tianyu Pang, Chao Du, Yinpeng Dong, and Jun Zhu
Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018
-
Adversarial Attacks and Defences Competition
Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, and Motoki Abe
NeurIPS 2017 Competition Chapter
-
Learning Visual Knowledge Memory Networks for Visual Question Answering
Zhou Su, Chen Zhu, Yinpeng Dong, Dongqi Cai, Yurong Chen, and Jianguo Li
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018
-
Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
Fangzhou Liao, Ming Liang, Yinpeng Dong, Tianyu Pang, Jun Zhu, and Xiaolin Hu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018
[code]
-
Boosting Adversarial Attacks with Momentum (Spotlight)
Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, and Jianguo Li
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018
[arXiv]
[non-targeted attack]
[targeted attack]
[cleverhans]
[poster]
-
Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization (Oral, Best Paper Nomination)
Yinpeng Dong, Renkun Ni, Jianguo Li, Yurong Chen, Jun Zhu, and Hang Su
British Machine Vision Conference (BMVC), London, UK, 2017
[code]
[slide]
[poster]
-
Forecast the Plausible Paths in Crowd Scenes
Hang Su, Jun Zhu, Yinpeng Dong, and Bo Zhang
International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017
-
Improving Interpretability of Deep Neural Networks with Semantic Information
Yinpeng Dong, Hang Su, Jun Zhu, and Bo Zhang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017
[arXiv]
[video]
[poster]
-
Efficient and Robust Semi-supervised Learning over a Sparse-Regularized Graph
Hang Su, Jun Zhu, Zhaozheng Yin, Yinpeng Dong, and Bo Zhang
European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 2016
-
Feature Engineering and Ensemble Modeling for Paper Acceptance Rank Prediction
Yujie Qian*, Yinpeng Dong*, Ye Ma*, Hailong Jin, and Juanzi Li (* indicates equal contribution)
SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) Workshop KDDCUP, San Francisco, USA, 2016
-
Crowd Scene Understanding with Coherent Recurrent Neural Networks
Hang Su, Yinpeng Dong, Jun Zhu, Haibin Ling, and Bo Zhang
International Joint Conference on Artificial Intelligence (IJCAI), New York, USA, 2016
[slide]
[poster]
Services
Organizer for:
CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems and Online Challenges (AML-CV)
Reviewer for:
TPAMI 2019, 2020, 2021
TIP 2019, 2020
TNNLS 2019, 2020
NeurIPS 2016, 2019, 2020
ICML 2019, 2021
CVPR 2019, 2020, 2021
ICLR 2020, 2021
ICCV 2019, 2021
ECCV 2020
AAAI 2019, 2020, 2021
IJCAI 2019, 2020
UAI 2019, 2021
Honors & Awards
- ByteDance Scholars Program, 2020.11
- Tsinghua-HUAWEI Scholarship, Tsinghua University, 2020.10
- Baidu Fellowship, 2020.01
- '84' Future Innovation Scholarship, CST Department of Tsinghua University, 2019.12
This award is given to Tianyu pang and me for our research on adversarial robustness.
- Microsoft Research Asia (MSRA) Fellowship, 2019.11
- China National Scholarship, Tsinghua University, 2019.10
- VALSE Annual Outstanding Student Paper Award, 2019.04
This award is given to "Boosting Adversarial Attacks with Momentum" in CVPR 2018.
- CCF-CV Academic Emerging Award (CCF-CV 学术新锐奖), 2018.11
Only 3 students in China were awarded for their research in computer vision during the first three years of Ph.D. career.
- China National Scholarship, Tsinghua University, 2018.10
- Tsinghua University Future PhD Fellowship, Tsinghua University, 2017.09
This fellowship was given to only 2 students in our department.
- Tsinghua Outstanding Graduates, Tsinghua University, 2017.06
Only 60 students in Tsinghua were awarded for their excellent performance during the four years of college life.
- Beijing Outstanding Graduates, 2017.06
- Outstanding Thesis, Tsinghua University, 2017.06
Thesis submitted for the degree of Bachelor of Engineering. Top-1 score in the Department of CST.
- Zhong Shimo Scholarship, Tsinghua University, 2016.12
The highest award in the Department of CST. Only 5 students (including undergraduate, master and Ph.D. students) are awarded each year.
- Zhong Shimo Scholarship, Tsinghua University, 2015.12
- The CCF Outstanding Undergraduate Award, CCF, 2015.06
Only 4 students in Tsinghua are awarded by China Computer Federation each year.
- ST Engineering Overseas Scholarship, Singapore Technologies Engineering, 2015.05
- China National Scholarship, Tsinghua University, 2014.10
Teaching
2019 spring, Head TA in Statistical Machine Learning, instructed by Prof. Jun Zhu
© 2020 Yinpeng Dong