|
I am now a Research Scientist in ZGC Lab, Beijing, China. I received the Ph.D. degree in 2022 from Beihang University (Summa Cum Laude), supervised by Prof. Wei Li and Prof. Xianglong Liu. Before that, I obtained my BSc degree in 2018 from Beihang University (Summa Cum Laude).
Github / Linkedin / Google Scholar / |
 |
|
My research interest is Trustworthy AI in Computer Vision, which consists of the physical adversarial examples generation, adversarial defense and evaluation. I hold the review that physical adversarial attacks and defenses can powerfully promote the development of secure and robust artificial intelligence, leading to a healthier future society. Now my research mainly includes:
|
[2023.10] One paper accepted by IEEE Symposium on Security and Privacy [2023.06] Two paper accepted by IJCAI-2023 GLOW and 人工智能(AI-View) [2023.04] One paper accepted by TPAMI. [2023.02] Two paper accepted by TNNLS and CVPR2023. [2023.01] Three paper accepted by 智能安全, Pattern Recognition, and USENIX Security Symposium. [2022.08] One paper accepted by ACM CCS 2022. [2022.07] One paper accepted by ACM MM 2022. |
 |
We propose a architecture-oritend transferable attack that could adverasially attack various VisionTransformers. |
 |
We generate defensive patches to help building robust recognition systems in practice against noises by simply sticking them on the target object. |
 |
We propose a bias-based framework to generate universal adversarial patches with strong generalization ability, which exploits the perceptual bias and attentional bias to improve the attacking ability. |
 |
We propose the Dual Attention Suppression (DAS) attack to generate visually-natural physical adversarial camouflages with strong transferability by suppressing both model and human attention. |
 |
We propose a bias-based framework to generate class-agnostic universal adversarial patches with strong generalization ability, which exploits both the perceptual and semantic bias of models. |
 |
|
 |
重明 is an open-source platform to evaluate model robustness and safety towards noises (e.g., adversarial examples, corruptions, etc.). The name is taken from the Chinese myth 重明鸟, which has strong power, could fight against beasts and avoid disasters. We hope our platform could improve the robustness of deep learning systems and help them to avoid safety-related problems. 重明 has been awarded the 首届OpenI启智社区优秀开源项目 (First OpenI Excellent Open Source Project). |
 |
RobustART is the first comprehensive Robustness investigation benchmark on large-scale dataset ImageNet regarding ARchitectural design (49 human-designed off-the-shelf architectures and 1200+ neural architecture searched networks) and Training techniques (10+ general ones e.g., extra training data, etc) towards diverse noises (adversarial, natural, and system noises). Our benchmark (including open-source toolkit, pre-trained model zoo, datasets, and analyses): (1) presents an open-source platform for conducting comprehensive evaluation on diverse robustness types; (2) provides a variety of pre-trained models with different training techniques to facilitate robustness evaluation; (3) proposes a new view to better understand the mechanism towards designing robust DNN architectures, backed up by the analysis. We will continuously contribute to building this ecosystem for the community. |
[2023]Invited as ICCV, ACM MM, IJCAI, CVPR, AAAI, IEEE TIP, ICME, Pattern Recognition Reviewer. [2022]Invited as NeurIPS, ACM MM, ECCV, CVPR, Reviewer. [2022] Co-organizer of the Workshop on International Workshop on The Art of Robustness: Devil and Angel in Adversarial Machine Learning at CVPR 2022. [2021]Invited as ACM MM, Pattern Recognition, IET Image Processing Reviewer. [2021] Co-organizer of the Forum on Safety and Privacy for Multimedia Systems at ChinaMM 2021. |
[2022.06] Outstanding Graduates of Beijing Province [2022.01] Beihang University Exploring Scholarship. [2021.10] Beihang University Guorui Scholarship. [2021.10] Beihang University Merit Student. [2021.06] Beihang University First Prize Scholarship. [2021.06] Beihang University Excellent Academic Paper Award. [2020.10] Beihang University First Prize Scholarship. [2020.09] China National Scholarship (Top2%). [2020.09] Beihang University Merit Student. [2019.10] Beihang University First Prize Scholarship. [2018.09] Beihang University Outstanding Freshman Scholarship (1/12). [2018.06] Outstanding Graduates of Beijing Province. |
|
|