The full list of publications can be found on Google Scholar.

2021

Noise Doesn’t Lie: Towards Universal Detection of Deep Inpainting
Ang Li, Qiuhong Ke, Xingjun Ma, Haiqin Weng, Zhiyuan Zong, Feng Xue, Rui Zhang
International Joint Conference on Artificial Intelligence (IJCAI), Virtual/Montreal, 2021.

Unlearnable Examples: Making Personal Data Unexploitable [Code] [Webpage]
Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang
International Conference on Learning Representations (ICLR), Virtual, 2021.(Spotlight, top 4%)
Press: MIT Technology Review, PURSUIT

Improving Adversarial Robustness via Channel-wise Activation Suppressing [Code]
Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang
International Conference on Learning Representations (ICLR), Virtual, 2021. (Spotlight, top 4%)

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks [Code]
Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma
International Conference on Learning Representations (ICLR), Virtual, 2021.

Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness
Linxi Jiang, Xingjun Ma, Zejia Weng, James Bailey, Yu-Gang Jiang
ICLR Workshop on Security and Safety in Machine Learning Systems, Virtual, 2021.

Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
Xingjun Ma*, Yuhao Niu*, Lin Gu, Yisen Wang, Yitian Zhao, James Bailey, Feng Lu
Pattern Recognition (PR), 110, 2021, 107332.
Press: Computer Vision News

RobOT: Robustness-Oriented Testing for Deep Learning Systems [Tookit]
Jingyi Wang, Jialuo Chen, Youcheng Sun, Xingjun Ma, Dongxia Wang, Jun Sun, Peng Cheng
International Conference on Software Engineering (ICSE), Virtual, 2021.

Dual Head Adversarial Training [Code]
Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani, James Bailey
International Joint Conference on Neural Networks (IJCNN), Virtual 2021.

Neural Architecture Search via Combinatorial Multi-Armed Bandit
Hanxun Huang, Xingjun Ma, Sarah M. Erfani, James Bailey
International Joint Conference on Neural Networks (IJCNN), Virtual 2021.

Federated Learning with Extreme Label Skew: A Data Extension Approach
Saheed Tijani, Xingjun Ma, Frank Jiang, Robin Doss
International Joint Conference on Neural Networks (IJCNN), Virtual 2021.

Microwave Link Failures Prediction via LSTM-based Feature Fusion Network
Zichan Ruan, Shuiqiao Yang, Lei Pan, Xingjun Ma, Wei Luo, Marthie Grobler
International Joint Conference on Neural Networks (IJCNN), Virtual 2021.

Sub-trajectory Similarity Join with Obfuscation
Yanchuan Chang, Jianzhong Qi, Egemen Tanin, Xingjun Ma, Hanan Samet
International Conference on Scientific and Statistical Database Management (SSDBM), Virtual, 2021.

Anomaly Detection for Scenario-based Insider Activities using CGAN Augmented Data
R G Gayathri, Atul Sajjanhar, Yong Xiang, Xingjun Ma
IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) 2021.

Surgical approach to the facial recess influences the acceptable trajectory of cochlear implantation electrodes
Bridget Copson, Sudanthi Wijewickrema, Xingjun Ma, Yun Zhou, Jean-Marc Gerard, Stephen O’Leary
European Archives of Oto-Rhino-Laryngology, 1-11, 2021.

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
Shihao Zhao, Xingjun Ma, Yisen Wang, James Bailey, Bo Li, Yu-Gang Jiang
arXiv preprint.

Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions
Nodens Koren, Qiuhong Ke, Yisen Wang, James Bailey, Xingjun Ma
arXiv preprint.

A Lazy Approach for Efficient Index Learning
Guanli Liu, Lars Kulik, Xingjun Ma, Jianzhong Qi
arXiv preprint.

2020

Normalized Loss Functions for Deep Learning with Noisy Labels [Code]
Xingjun Ma*, Hanxun Huang*, Yisen Wang, Simone Romano, Sarah Erfani, James Bailey
International Conference on Machine Learning (ICML), Virtual, 2020.

Improving Adversarial Robustness Requires Revisiting Misclassified Examples [Code]
Yisen Wang, Difan Zou, Jinfeng Yi, James Bailey, Xingjun Ma, Quanquan Gu
International Conference on Learning Representations (ICLR), Virtual, 2020.

Skip Connections Matter: on the Transferability of Adversarial Examples Generated with ResNets [Code]
Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey, Xingjun Ma
International Conference on Learning Representations (ICLR), Virtual, 2020. (Spotlight, top 4%)

Clean-Label Backdoor Attacks on Video Recognition Models [Code]
Shihao Zhao, Xingjun Ma, Xiang Zheng, James Bailey, Jingjing Chen, Yu-Gang Jiang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, 2020.

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles [Code]
Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, Kai Qin, Yun Yang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, 2020.

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks [Code]
Yunfei Liu, Xingjun Ma, James Bailey, Feng Lu
European Conference on Computer Vision (ECCV), Virtual, 2020.

Short-Term and Long-Term Context Aggregation Network for Video Inpainting
Ang Li, Shanshan Zhao, Xingjun Ma, Mingming Gong, Jianzhong Qi, Rui Zhang, Dacheng Tao, Ramamohanarao Kotagiri
European Conference on Computer Vision (ECCV), Virtual, 2020. (Spotlight, top 5%)

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection [Dataset/Code]
Bojia Zi, Jingjing Chen, Minghao Chang, Xingjun Ma, Yu-Gang Jiang
ACM International Conference on Multimedia (ACMMM), Virtual, 2020.

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
Lingjuan Lyu, Yitong Li, Karthik, Nandakumar, Jiangshan Yu, Xingjun Ma
IEEE Transactions on Dependable and Secure Computing (TDSC). (accepted in 2020)

Towards Fair and Privacy-Preserving Federated Deep Models [Code] [Medium] [Youtube]
Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin, Han Yu, and Kee Siong Ng
IEEE Transactions on Parallel and Distributed Systems (TPDS). (accepted in 2020)

Transfer of Automated Performance Feedback Models to Different Specimens in Virtual Reality Temporal Bone Surgery
Jesslyn Lamtara, Nathan Hanegbi, Benjamin Talks, Sudanthi Wijewickrema, Xingjun Ma, Patorn Piromchai, James Bailey and Stephen O’Leary
International Conference on Artificial Intelligence in Education (AIED), Ifrane, Morocco, 2020.

Privacy and Robustness in Federated Learning: Attacks and Defenses
Lingjuan Lyu, Han Yu, Xingjun Ma, Lichao Sun, Jun Zhao, Qiang Yang, Philip S. Yu
arXiv preprint.

2019

On the Convergence and Robustness of Adversarial Training [Code]
Yisen Wang*, Xingjun Ma*, James Bailey, Jinfeng Yi, Bowen Zhou, Quanquan Gu
International Conference on Machine Learning (ICML), Long Beach, USA, 2019. (Long talk, top 3%)

Symmetric Cross Entropy for Robust Learning with Noisy Labels [Code]
Yisen Wang*, Xingjun Ma*, Zaiyi Chen, Yuan Luo, Jinfeng Yi, James Bailey
International Conference on Computer Vision (ICCV), Seoul, Korea, 2019.

Black-box Adversarial Attacks on Video Recognition Models [Code]
Linxi Jiang*, Xingjun Ma*, Shaoxiang Chen, James Bailey, Yu-Gang Jiang
ACM International Conference on Multimedia (ACMMM), Nice, France, 2019.

Generative Image Inpainting with Submanifold Alignment
Ang Li, Jianzhong Qi, Rui Zhang, Xingjun Ma, Ramamohanarao Kotagiri
International Joint Conference on Artificial Intelligence (IJCAI), Macao, China, 2019.

Exploiting Patterns to Explain Individual Predictions
Yunzhe Jia, James Bailey, Ramamohanarao Kotagiri, Christopher Leckie, Xingjun Ma
Knowledge and Information Systems (KAIS). (accepted in 2019)

2018

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality [Code]
Xingjun Ma, Bo Li, Yisen Wang, Sarah M. Erfani, Sudanthi Wijewickrema, Grant Schoenebeck, Dawn Song, Michael E. Houle, James Bailey
International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 2018, (Oral, top 2%)

Dimensionality-Driven Learning with Noisy Labels [Code]
Xingjun Ma*, Yisen Wang*, Michael E. Houle, Shuo Zhou, Sarah Monazam Erfani, Shu-Tao Xia, Sudanthi Wijewickrema, James Bailey
International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018. (Long talk, top 4%)

Iterative Learning with Open-set Noisy Labels
Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, 2018. (Spotlight, top 6%)

Providing Automated Real-Time Technical Feedback for Virtual Reality Based Surgical Training: Is the Simpler the Better?
Sudanthi Wijewickrema, Xingjun Ma, Patorn Piromchai, Robert Briggs, James Bailey, Gregor Kennedy, Stephen O’Leary
International Conference on Artificial Intelligence in Education (AIED), London, UK, 2018

Development and Validation of a Virtual Reality Tutor to Teach Clinically Oriented Surgical Anatomy of the Ear
Sudanthi Wijewickrema, Bridget Copson, Xingjun Ma, Robert Briggs, James Bailey, Gregor Kennedy and Stephen O’Leary
International Symposium on Computer-Based Medical Systems (CBMS), 2018

2017

Adversarial Generation of Real-time Feedback with Neural Networks for Simulation-based Training
Xingjun Ma, Sudanthi Wijewickrema, Shuo Zhou, Yun Zhou, Zakaria Mhammedi, Stephen O’Leary, James Bailey.
International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017. (Oral)

Unbiased Multivariate Correlation Analysis
Yisen Wang, Simone Romano, Nguyen Xuan Vinh, James Bailey, Xingjun Ma, Shu-Tao Xia
AAAI Conference on Artificial Intelligence (AAAI), San Francisco, USA, 2017. (Oral)

Providing Effective Real-time Feedback in Simulation-based Surgical Training
Xingjun Ma, Sudanthi Wijewickrema, Yun Zhou, Shuo Zhou, Stephen O’Leary, James Bailey
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Quebec City, Canada, 2017.

Simulation for Training Cochlear Implant Electrode Insertion
Xingjun Ma, Sudanthi Wijewickremay, Yun Zhou, Bridget Copson, James Bailey, Gregor Kennedy, Stephen O’Leary
International Symposium on Computer-Based Medical Systems (CBMS), Thessaloniki, Greece, 2017

Design and Evaluation of a Virtual Reality Simulation Module for Training Advanced Temporal Bone Surgery
Sudanthi Wijewickremay, Bridget Copson, Yun Zhou, Xingjun Ma, Robert Briggs, James Bailey, Gregor Kennedy, Stephen O’Leary
International Symposium on Computer-Based Medical Systems (CBMS), Thessaloniki, Greece, 2017

2016

Finding Influentials in Twitter: A Temporal Influence Ranking Model [Paper]
Xingjun Ma, Chunping Li, James Bailey, Sudanthi Wijewickrema
Australasian Data Mining (AusDM), Canberra, Australia, 2016