Chaowei Xiao
Email: xiaocw [at] asu [dot] edu
I am Chaowei Xiao, an assistant professor in the Computer Science Department at Arizona State University and a research scientist at NVIDIA Research.
My research interests lie at the intersection of computer security, privacy, and machine learning, with the goal to build the socially responsible machine learning systems.
I obtained my PhD degree in Computer Science and Engineering Department from University of Michigan, Ann Arbor and my bachelor's degree in School of Software from Tsinghua University in 2020 and 2015 respectively.
My group has multiple positions for PhD student, Summer interns and Visiting students for Fall 2023. If you are interested, please send me an email with your CV, and publications (if any).
Recent News
- [09/2022] One papers got accepted to at USENIX Security 2023.
- [09/2022] Two papers got accepted to at NeurIPS 2022.
- [09/2022] Our paper RobustTraj has been accepted to CORL for oral presentations. We explore to train a robust Trajectory Prediction Model against adversarial attacks.
- [08/2022] I have moved to Phoenix and joined ASU as an assisatnt professor. I plan to get 2-3 PhD students for Fall 2023. Please send me an email with you CV if you are interested.
- [08/2022] I will be giving a talk in virtual seminar series on Challenges and Opportunities for Security & Privacy in Machine Learning.
- [07/2022] One papers got accepted to ACM Computing Survey 2022.
- [07/2022] Two papers got accepted to ECCV 2022.
- [05/2022] Two papers got accepted to ICML 2022. Thanks for all of my collaborators.
- [3/2022] I will be giving a talk in AAAI 2022 1st International Workshop on Practical Deep Learning in the Wild.
- [3/2022] I will be giving a talk in AAAI 2022 workshop on Adversarial Machine Learning and Beyond.
- [2/2022] One paper is accepted to ICLR.
- [12/2021] One paper on exploring the robustness of RL got accepted to AAMAS after a long journey.
- [11/2021] One paper got accepted to INFOCOM.
- [09/2021] Three papers got accepted to NeurIPS. Thanks for all of my collaborators.
- [08/2021] I gave a talk at Tsinghua University
- [07/2021] One paper is accepted to ICCV.
- [07/2021] I am serving as an Area Chair for AAAI 2022.
- [06/2021] I gave a talk in CVPR 2021 Tutorial on Adversarial Machine Learning in Computer Vision.
- [04/2021] One paper is accepted to IEEE S&P.
- [03/2021] Best Paper Award at ESWN 2021
- [11/2020]: One paper is accepted to NeurIPS’20 .
- [11/2020]: One paper is accepted to NeurIPS’20 .
- [06/2020]: One paper is accepted to ECCV’20 .
- [12/2019]: One paper is accepted to ICLR’20 .
- [08/2019]: Our generated physical adversarial Stop Sign used in our CVPR’18 is on display at Science Museum in London.
- [07/2019]: One paper is accepted to ICDM 2019.
- [03/2019]: Our paper "MeshAdv: Adversarial Meshes for Visual Recognition" is accepted to CVPR 2019 as oral presentation.
- [03/2019]: We will organize the workshop on Adversarial Machine Learning in Real-World Computer Vision Systems at CVPR 2019. Please submit your papers.
More
Events
- [Workshop@ICLR2022] I am organizing the Workshop on Socially Responsible Machine Learning in ICLR 2022.
- [Call For Paper] I am serving as the Guest Editor of Frontiers in Big Data: Trustworthy Machine Learning.
- [Workshop@ICCV2021] I am co-organizing the Workshop on Neural Architectures: Past, Present and Future in ICCV 2021.
- [Workshop@ICML2021] I co-organized the Workshop on Socially Responsible Machine Learning in ICML 2021.
- [Workshop@ACMMM2021] I co-organized the Workshop on 1st International Workshop on Adversarial Learning for Multimedia in ACM-MM 2021.
- [Workshop@CVPR2019] I co-organized the Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems. in CVPR 2019.
Publications
(* represents equal contribution)
2022
- Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, Chaowei Xiao
- Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Boxin Wang, Wei Ping, Chaowei Xiao, Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Bo Li, Anima Anandkumar, Bryan Catanzaro.
- Robust Trajectory Prediction against Adversarial Attacks
Yulong Cao, Danfei Xu, Xinshuo Weng, Z. Morley Mao, Anima Anandkuma, Chaowei Xiao, Marco Pavone
- Diffusion Models for Adversarial Purification
Weili Nie, Brandon Guo, Yujia Huang,Chaowei Xiao, Arash Vahdat, Anima Anandkumar.
- Understanding the robustness in vision transformers.
Daquan Zhou, Zhiding Yu, Enze Xie,Chaowei Xiao, Anima Anandkumar, Jiashi Feng, Jose M Alvarez.
- AdvDO: Realistic Adversarial Attacks for
Trajectory Prediction
Yulong Cao,Chaowei Xiao, Anima Anandkumar, Danfei Xu, Marco Pavone.
- SecretGen: Privacy Recovery on Pre-trained Models
Zhuowen Yuan, Fan Wu, Yunhui Long,Chaowei Xiao, Bo Li
- Taxonomy of Machine Learning Safety: A Survey and Primer
Sina Mohseni, Zhiding Yu, Chaowei Xiao Jay Yadawa, Haotao Wang and Zhangyang Wang
ACM Computing Survey 2022[pdf]
- RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
Xiaojian Ma, Weili Nie, Zhiding Yu, Huaizu Jiang,Chaowei Xiao, Yuke Zhu, Song-Chun Zhu, Anima Anandkumar
- Characterizing Attacks on Deep Reinforcement Learning.
Xinlei Pan*,Chaowei Xiao*, Warren He, Shuang Yang, Peng Jian, Mingjie Sun, Mingyan Liu, Bo Li, Dawn Song.
AAMAS 2022 [pdf]
2021
- Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions.
Jiachen Sun, Yulong Cao, Christopher Choy, Zhiding Yu, Anima Anandkumar, Z. Morley Mao, Chaowei Xiao.
NeurIPS 2021
- AugMax: Adversarial Composition of RandomAugmentations for Robust Training.
Haotao Wang,Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Animashree Anandkumar, Zhangyang Wang.
NeurIPS 2021
- Efficient Transformers for Language and Vision.
Chen Zhu, Wei Ping,Chaowei Xiao, Mohammad Shoeybi, Tom Goldstein, Anima Anandkumar, Bryan Catanzaro.
NeurIPS 2021 (84.1% Top-1 accuracy solely trained on ImageNet-1K)
- Can Shape Structure Features Improve Model Robustness?
Mingjie Sun*, Zichao Li*,Chaowei Xiao*, Haonan Qiu, Bhavya Kailkhura, MingyanLiu, Bo Li.
ICCV 2021
- Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks.
Yulong Cao*, Ningfei Wang*,Chaowei Xiao*, Dawei Yang*, Jin Fang, RuigangYang, Qi Alfred Chen, Mingyan Liu, Bo Li.
IEEE Symposium on Security and Privacy (Oakland) 2021
- Application-Driven Privacy-Preserving Data Publishing with Correlated Attributes.
Aria Rezaei,Chaowei Xiao, Jie Gao, Bo Li, Sirajum Munir.
Embedded Wireless Systems and Networks (EWSN 2021)Best Paper Award
- Behavior Privacy Perserving in RF Sensing.
Jianwie Liu,Chaowei Xiao, Kaiyan Cui, Jinsong Han, Xian Xu, Kui Ren.
IEEE Transcations on Dependable and Secure Computing. [pdf]
2020
- SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
Haonan Qiu*, Chaowei Xiao*, Lei Yang*, Xinchen Yan, Honglak Lee, Bo Li.
ECCV 2020
- Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
Huan Zhang*, Hongge Chen*, Chaowei Xiao, Bo Li, Mingyan Liu, Duane Boning, Cho-Jui Hsieh.
NeurIPS 2020 (Spotlight).
- Towards Stable and Efficient Training of Verifiably Robust Neural Networks
Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth, Bo Li, Duane Boning, Cho-Jui Hsieh.
ICLR 2020.
2019
- AdvIT: Adversarial Frames Identifier Based on Temporal Consistency In Videos
Chaowei Xiao, Ruizhi Deng, Bo Li, Taesung Lee, Jinfeng Yi, Ian Molloy, Mingyan Liu, Dawn Song
In International Conference on Computer Vision (ICCV) 2019.
- MeshAdv: Adversarial Meshes for Visual Recognition
Chaowei Xiao*, Dawei Yang*, Bo Li, Jia Deng, Mingyan Liu
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019. (Oral presentation) [pdf]
- Performing Co-Membership Attack Against Deep Generative Model
Kin Sum Liu, Chaowie Xiao , Bo Li, Jie Gao
In IEEE International Conference on Data Mining (ICDM) 2019
- Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features
Liang Tong, Bo Li, Chen Hajaj, Chaowei Xiao, Ning Zhang, Yevgeniy Vorobeychik.
In USENIX Security 2019.
- Adversarial Sensor Attack on LIDAR-based Perception in Autonomous Driving
Yulong Cao, Chaowei Xiao, Benjamin Cyr, Yimeng Zhou, Won Park, Sara Rampazzi, Qi Alfred Chen, Kevin Fu, Z. Morely Map
In the 26th ACM Conference on Computer and Communications Security (CCS'19) [pdf]
2018
- Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
Chaowei Xiao, Duizhi Deng, Bo Li, Fisher Yu, Mingyan Liu and Dawn Song
In European Conference on Computer Vision (ECCV), 2018 [pdf][supplementary material]
- Spatially Transformed Adversarial Examples
Chaowei Xiao*, Jun-Yan Zhu*, Bo Li, Warren He, Mingyan Liu and Dawn Song
In International Conference on Learning Representations (ICLR), 2018 [pdf]
- Generating Adversarial Examples with Adversarial Networks
Chaowei Xiao, Bo Li, Jun-Yan Zhu, Warren He, Mingyan Liu and Dawn Song
In International Joint Conference on Artificial Intelligence (IJCAI), 2018. [pdf]
- From Behavior Similarity to Symptom Similarity: Using Community Detection for Early Discovery of Software Exploits
Chaowei Xiao, Armin Sarabi,Yang Liu , Bo Li, Mingyan Liu and Tudor Dumitras
In USENIX Security Symposium (USENIX Security), 2018 [pdf]
- Robust Physical-World Attacks on Machine Learning Models
Kevin Eykholt*, Ivan Evtimov*, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno and Dawn Song
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 [pdf]
Before 2018
- Static Power of Mobile Devices: Self-updating Radio Maps for Wireless Indoor Localization
Chenshu Wu, Zheng Yang, Chaowei Xiao, Chaofan Yang, Yunhao Liu and Mingyan Liu
In IEEE International Conference on Computer Communications (INFOCOM), 2015
- Tagoram: Real-time Tracking of Mobile RFID Tags to High Precision Using COTS Devices.
Lei Yang, Yekui Chen, Xiangyang Li, Chaowei Xiao, Mo Li and Yunhao Liu
In International Conference on Mobile Computing and Networking (MobiCom), 2014. Best Paper Award
