Xingjun (Daniel) Ma - AI Profile

Information

Assistant Professor

School of Information Technology, Deakin University

Experience

Education

Bio

Assistant professor in the School of Information technology, Deakin University, honorary fellow in the School of Computing and Information Systems, The University of Melbourne. My research focus is adversarial machine learning.

Research Interests

Papers30 papers

Sort

By YearBy Citation

Add Paper

Neural Architecture Search via Combinatorial Multi-Armed Bandit

Hanxun Huang,Xingjun Ma,Sarah M. Erfani,James Bailey

Bibtex

Improving Adversarial Robustness via Channel-wise Activation Suppressing

Yang Bai, Yuyuan Zeng,Yong Jiang,Shu-Tao Xia,Xingjun Ma,Yisen Wang

ICLR, (2021)

EIBibtex

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

Bibtex

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

Yige Li, Nodens Koren, Lingjuan Lyu, Xixiang Lyu,Bo Li,Xingjun Ma

Bibtex

Unlearnable Examples: Making Personal Data Unexploitable

Hanxun Huang,Xingjun Ma,Sarah Monazam Erfani,James Bailey,Yisen Wang

ICLR, (2021)

EIBibtex

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, (2021): 107332

EIBibtex

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

Dongxian Wu,Yisen Wang, Shu-Tao Xia,James Bailey,Xingjun Ma

ICLR, (2020)

EIBibtex

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

Yunfei Liu,Xingjun Ma,James Bailey,Feng Lu

european conference on computer vision, pp.182-199, (2020)

Bibtex

Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness

Linxi Jiang,Xingjun Ma, Zejia Weng,James Bailey,Yu-Gang Jiang

Cited by5Bibtex

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles

Duan Ranjie,Ma Xingjun,Wang Yisen,Bailey James,Qin A. K.,Yang Yun

CVPR, pp.997-1005, (2020)

EIBibtex

Clean-Label Backdoor Attacks on Video Recognition Models

Zhao Shihao,Ma Xingjun, Zheng Xiang,Bailey James,Chen Jingjing,Jiang Yu-Gang

CVPR, pp.14431-14440, (2020)

Cited by11EIBibtex

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

Bojia Zi, Minghao Chang,Jingjing Chen,Xingjun Ma,Yu-Gang Jiang

MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA ..., pp.2382-2390, (2020)

Cited by3EIBibtex

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

Yige Li,Xingjun Ma, Nodens Koren, Lingjuan Lyu, Xixiang Lyu,Bo Li

international conference on learning representations, (2020)

Bibtex

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

Dongxian Wu,Yisen Wang,Shu-Tao Xia,James Bailey,Xingjun Ma

ICLR, (2020)

Cited by3EIBibtex

Exploiting patterns to explain individual predictions

Yunzhe Jia,James Bailey,Kotagiri Ramamohanarao,Christopher Leckie,Xingjun Ma

Knowledge and Information Systems, no. 3 (2020): 927-950

Cited by2EIBibtex

Privacy and Robustness in Federated Learning: Attacks and Defenses

Lingjuan Lyu,Han Yu,Xingjun Ma,Lichao Sun, Jun Zhao,Qiang Yang,Philip S. Yu

Bibtex

Generative Image Inpainting with Submanifold Alignment

Ang Li,Jianzhong Qi,Rui Zhang,Xingjun Ma,Kotagiri Ramamohanarao

IJCAI, pp.811-817, (2019)

Cited by3EIBibtex

On the Convergence and Robustness of Adversarial Training

Yisen Wang,Xingjun Ma,James Bailey,Jinfeng Yi,Bowen Zhou,Quanquan Gu

international conference on machine learning, (2019)

Cited by33EIBibtex

Towards Fair and Decentralized Privacy-Preserving Deep Learning with Blockchain

Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar,Yitong Li,Xingjun Ma,Jiong Jin

CoRR, (2019)

Cited by2EIBibtex

Quality Evaluation of GANs Using Cross Local Intrinsic Dimensionality

Sukarna Barua,Xingjun Ma,Sarah Monazam Erfani,Michael E. Houle,James Bailey

arXiv: Learning, (2019)

Cited by3EIBibtex

View All

Ego Network

D-Core

Author Statistics

Xingjun (Daniel) MaAssistant Professor

Papers30 papers