Sotabase

Career

· Senior Research Scientist, Sea2024–
· Research Scientist, Sea2022–2024
· Visiting Student Researcher, Stanford University2020–2020
· Doctor of Philosophy - PhD, Computer Science, Tsinghua University2017–2022
· Visiting Student Researcher, Carnegie Mellon University2016–2016

Publications (0)

Boosting Adversarial Attacks with Momentum
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
3,126
cited
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
Computer Vision and Pattern Recognition · 2019
1,026
cited
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
992
cited
Understanding R1-Zero-Like Training: A Critical Perspective
arXiv.org · 2025
680
cited
Improving Adversarial Robustness via Promoting Ensemble Diversity
International Conference on Machine Learning · 2019
485
cited
Adversarial Attacks and Defences Competition
arXiv.org · 2018
342
cited
LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
arXiv.org · 2023
303
cited
Improving Black-box Adversarial Attacks with a Transfer-based Prior
Neural Information Processing Systems · 2019
297
cited
Benchmarking Adversarial Robustness on Image Classification
Computer Vision and Pattern Recognition · 2020
289
cited
Bag of Tricks for Adversarial Training
International Conference on Learning Representations · 2020
284
cited
Better Diffusion Models Further Improve Adversarial Training
International Conference on Machine Learning · 2023
284
cited
On Evaluating Adversarial Robustness of Large Vision-Language Models
Neural Information Processing Systems · 2023
276
cited
Towards Robust Detection of Adversarial Examples
Neural Information Processing Systems · 2017
231
cited
Boosting Adversarial Training with Hypersphere Embedding
Neural Information Processing Systems · 2020
164
cited
A Recipe for Watermarking Diffusion Models
arXiv.org · 2023
162
cited
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
International Conference on Machine Learning · 2022
151
cited
Adversarial Distributional Training for Robust Deep Learning
Neural Information Processing Systems · 2020
144
cited
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
Neural Information Processing Systems · 2024
126
cited
Black-box Detection of Backdoor Attacks with Limited Information and Data
IEEE International Conference on Computer Vision · 2021
125
cited
Efficient Diffusion Policies for Offline Reinforcement Learning
Neural Information Processing Systems · 2023
122
cited
Sotabase