Publications

You can also find my articles on my Google Scholar profile.

Improving Adversarial Transferability via Model Alignment [ paper ]
Avery Ma, Amir-massoud Farahmand, Yangchen Pan, Philip Torr, Jindong Gu
Under Review, 2023

A Survey on Transferability of Adversarial Examples across Deep Neural Networks [ paper ]
Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqain Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip Torr
Under Review, 2023

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods [ blog ] [ paper ] [ code ]
Avery Ma, Yangchen Pan, Amir-massoud Farahmand
In Transactions on Machine Learning Research (TMLR) with Featured Certification (Top 3% of Accepted Papers)

SAGE: Saliency-Guided Mixup with Optimal Rearrangements [ paper ] [ code ]
Avery Ma, Nikita Dvornik, Ran Zhang, Leila Pishdad, Konstantinos G. Derpanis, Afsaneh Fazly
In British Machine Vision Conference (BMVC), 2022

Improving Hierarchical Adversarial Robustness of Deep Neural Networks [ paper ]
Avery Ma, Aladin Virmaux, Kevin Scaman, Juwei Lu
Preprint, 2021

SOAR: Second-Order Adversarial Regularization [ paper ]
Avery Ma, Fartash Faghri, Nicolas Papernot, Amir-massoud Farahmand
Preprint, 2020

Deep learning-driven depth from defocus via active multispectral quasi-random projections with complex subpatterns [ paper ]
Avery Ma, Alexander Wong, David Clausi
In Conference on Computer and Robot Vision (CRV), 2018

Real-time spatial-based projector resolution enhancement [ paper ]
Avery Ma, Ahmed Gawish, Mark Lamm, Alexander Wong, Paul Fieguth
In Society for Information Display (SID) Symposium Digest of Technical Papers, 2018

An inverse problem approach to computational active depth from defocus [ paper ] [ code ]
Avery Ma, Alexander Wong
In Journal of Physics: Conference Series, 2018

Depth from defocus via active multispectral quasi-random point projections using deep learning [ paper ] [ code ]
Avery Ma, Alexander Wong, David Clausi
In Conference on Vision and Imaging Systems (CVIS), 2017

Motion detection in high resolution enhancement [ paper ]
Xiaodan Hu, Avery Ma, Ahmed Gawish, Mark Lamm, Paul Fieguth
In Conference on Vision and Imaging Systems (CVIS), 2017

Depth from defocus via active quasi-random point projections: a deep learning approach [ paper ] [ code ]
Avery Ma, Alexander Wong, David Clausi
In International Conference on Image Analysis and Recognition (ICIAR), 2017

Enhanced depth from defocus via active quasi-random colored point projections [ paper ] [ code ]
Avery Ma, Alexander Wong
In International Conference on Inverse Problems in Engineering (ICIPE), 2017

Depth from defocus via active quasi-random point projections [ paper ] [ code ]
Avery Ma, Alexander Wong
In Conference on Vision and Imaging Systems (CVIS), 2016

Patents

SAGE: Saliency-Guided Mixup with Optimal Re-arrangements for Efficient Data Augmentation
Avery Ma, Nikita Dvornik, Ran Zhang, Konstantinos Derpanis, Afsaneh Fazly
Patent Pending

Real-time spatial-based resolution enhancement using shifted superposition
Avery Ma, Ahmed Gawish, Mark Lamm, Alexander Wong, Paul Fieguth
Patent No.: [ 10009587 B1 ]

Thesis

Computational Depth from Defocus via Active Quasi-random Pattern Projections [ pdf ]
Avery Ma
University of Waterloo MASc Thesis

Projects

RideOn - All Terrain Personal Transportation Device [ video ]
Avery Ma, Jonathan Tham, Terry Yang, Chris Song, Terry Ho
University of Waterloo 2016 Mechatronics Engineering Capstone Design Project