Welcome to my homepage!
E-mail: lixuwang2025@u.northwestern.edu
Address: L476, Technological Institute, 2145 Sheridan Road, Evanston, IL, USA
This is Lixu Wang. I am a Ph.D. candidate in Computer Science at Northwestern University (NU) starting in Spring 2021, advised by Prof. Qi Zhu and Prof. Xiao Wang, and partially supported by IBM PhD Fellowship. Prior to Northwestern, I obtained my B.E. from Zhejiang University (ZJU) in July 2020 under the supervision of Prof. Wenyuan Xu. I am open to all kinds of collaboration, please drop me an email if you are interested in my research.
Recent News
03/2024: Papers about FL and Image Retrieval have been submitted to ECCV 2024.
02/2024: Papers about Time-Series Analysis and Survey of Dynamic FL have been submitted to ICML 2024 and IJCAI 2024.
12/2023: Help to submit one NSF proposal with CISPA.
12/2023: Our paper about anomaly detection has been accepted by ICASSP 2024.
09/2023: Our paper about data IP has been accepted by NeurIPS 2023.
08/2023: Super excited to be an IBM PhD Fellowship recipient.
07/2023: Our paper about backdoor detection has been accepted by ICCV 2023.
04/2023: Help to submit two NSF proposals.
01/2023: Our paper about domain generalization has been accepted by ICLR 2023.
11/2022: Become a visiting research scientist at General Motors.
03/2022: Our paper about incremental learning is accepted by CVPR 2022.
02/2022: Our paper about incremental learning is accepted by TNNLS 2021.
01/2022: Our paper about model IP is accepted by ICLR 2022 as an oral presentation.
07/2021: Our paper about domain adaptation is accepted by ICCV 2021.
03/2021: Our paper about digital watermarks is accepted by USENIX Security 2021.
12/2020: Our paper about federated learning is accepted by AAAI 2021.
06/2020: Received Outstanding Undergraduate Dissertation Award of ZJU.
Research Interest
I aim to create socially responsible machine learning (ML) models, i.e., ML models that can protect the privacy of their training data and minimize the chance of being misused. In particular, to ensure privacy protection, those models must be resistant to various privacy attacks. To prevent harmful social impacts from the misuse of ML models, their generalization ability on unintentional data domains and tasks must be reduced. To achieve these goals, I have been developing novel ML models and tools with a diverse set of techniques in Optimization Theory, Information Theory, and Cryptography. Greater ability comes with greater responsibility, and this applies equally to ML technology. ML models with social responsibility can protect data privacy and prevent serious consequences caused by the harmful use of models, such as teenagers obtaining violent information from recommendation systems or criminals using ML models to engage in criminal activities.
In particular, my current research lies in:
Model Protection (ICLR-2022, NeurIPS 2023, Working-2023-a)
Federated Learning (AAAI-2021, CVPR-2022, Working-2023-b)
Out-of-distribution Generalization (ICCV-2021, TNNLS-2022, ICLR-2023, ICASSP-2024, Working-2023-b, Working-2023-c)
Crypto-ML and ML Security (Usenix-2021, ICCV-2023, Working-2023-d)
Selected Publications ( * denotes equal contribution, ** denotes alphabetical order, # denotes corresponding authors)
Federated Learning with New Knowledge: Fundamentals, Advances, and Futures
/code /slides /poster /video
Lixu Wang*, Yang Zhao*, Jiahua Dong, Ating Yin, Qinbin Li, Xiao Wang, Dusit Niyato, Qi Zhu
Under Review
Phase-driven Domain Generalizable Learning for Nonstationary Time Series
/code /slides /poster /video
Payal Mohapatra*, Lixu Wang*, Qi Zhu
Under Review
Federated Continual Novel Class Learning
/code /slides /poster /video
Lixu Wang*, Chenxi Liu*, Junfeng Guo, Jiahua Dong, Xiao Wang, Heng Huang, Qi Zhu
Under Review
DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series Anomaly Detection
/code /slides /poster /video
Lixu Wang, Shichao Xu, Xinyu Du, Qi Zhu
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)
Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
/code /slides /poster /video
Junfeng Guo, Yiming Li, Lixu Wang, Shu-Tao Xia, Heng Huang, Cong Liu, Bo Li
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
PolicyCleanse: Detecting and Mitigating Trojan Attacks in Reinforcement Learning
/code /slides /poster /video
Junfeng Guo, Ang Li, Lixu Wang, Cong Liu
IEEE/CVF International Conference on Computer Vision (ICCV 2023)
Deja Vu: Continual Model Generalization for Unseen Domains
/code /slides /poster /video
Chenxi Liu**, Lixu Wang**#, Lingjuan Lu, Chen Sun, Xiao Wang, Qi Zhu
The 11th International Conference on Learning Representations (ICLR 2023)
Federated Class Incremental Learning
/code /slides /poster /video
Jiahua Dong**, Lixu Wang**, Zhen Fang, Gan Sun, Shichao Xu, Xiao Wang, Qi Zhu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)
Weak Adaptation Learning - Addressing Cross-domain Data Insufficiency with Weak Annotator
/code /slides /poster /video
Shichao Xu*, Lixu Wang*, Yixuan Wang, Qi Zhu
IEEE/CVF International Conference on Computer Vision (ICCV 2021)
mID: Tracing Screen Photos via Moiré Patterns
/code /slides /poster /video
Yushi Cheng, Xiaoyu Ji, Lixu Wang*, Qi Pang*, Yichao Chen, Wenyuan Xu
30th USENIX Security Symposium (USENIX Security 2021)
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation
Jiahua Dong, Gan Sun, Lixu Wang, Jun Li
IEEE Transactions on Neural Networks and Learning Systems (TNNLS 2022)
Services
Talks
'Machine Learning with Data Constraints from Generalization', Zhejiang University, June 2022, Hangzhou.
'Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization', May 2022, Sony AI.
'Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization' on ICLR 2022, April 2022, Virtual.
'Federated Class Incremental Learning' on SFFAI, April 2022, Virtual
'Addressing Class Imbalance in Federated Learning' on AAAI 2021, Feb 2021, Virtual.
Reviewer / Program Committee
CVPR: 2022, 2023, 2024
ICCV: 2023
ECCV: 2024
ICLR: 2024
NeurIPS: 2022, 2023
AAAI: 2022, 2023
WACV: 2023, 2024
Pattern Recognition, TCSVT, IEEE MSN 2023
External Reviewer for ICCAD 2021; RTAS 2022; DATE 2023; ASP-DAC 2023
Academic Performance: 4.0/4.0 (NU), 3.96/4.0 (ZJU)
Collaborators: Jiahua Dong (CAS); Junfeng Guo (UMaryland); Qi Pang (CMU); Zhen Fang (UTS); Yiming Li (ZJU); Yang Zhao (AStar); Qinbin Li (UCB)
Advising: Ruiqi Xu (B.S. at NU, now Ph.D. at Uchicago), Xiangyu Shi (B.E. at ZJU); Chenxi Liu (M.S. at NU, now Ph.D. at UMaryland Park), Jinjin Cai (M.S. at NU, now Ph.D. at Purdue), Yufei Wang (M.S. at NU, now Ph.D. at Northeastern), Shiyuan Duan (M.S. at NU), Yueyuan Sui (M.S. at NU), Bingqi Shang (M.S. at NU)