Robust Training

Robust training aims to develop machine learning models that are resilient to various forms of noise and uncertainty, including data imperfections, adversarial attacks, and distribution shifts. Current research focuses on improving model robustness across diverse applications and data types, employing techniques like adversarial training, data augmentation strategies (e.g., Mixup, diffusion-based variations), and novel loss functions that incorporate noise governance or margin maximization. These advancements are crucial for deploying reliable and trustworthy AI systems in real-world scenarios, particularly in safety-critical applications where model performance under uncertainty is paramount.

Papers

October 18, 2022

Not All Poisons are Created Equal: Robust Training against Data Poisoning
Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman
Poisoning Attack Data Poisoning Attack Robust Training Data Poisoning State of the Art Defense Targeted Attack Poisoning Efficiency

October 13, 2022

COLLIDER: A Robust Training Framework for Backdoor Data
Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie
Deep Neural Network Adversarial Training Backdoor Attack Robust Training Backdoor Learning Backdoor Data

October 5, 2022

On Adversarial Robustness of Deep Image Deblurring
Kanchana Vaishnavi Gandikota, Paramanand Chandramouli, Michael Moeller
Adversarial Attack Adversarial Robustness Robust Training Deep Image Image Recovery Based Image

September 13, 2022

Adversarial Coreset Selection for Efficient Robust Training
Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie
Adversarial Attack Adversarial Example Adversarial Training Robust Training COreset Selection

August 19, 2022

A Novel Plug-and-Play Approach for Adversarially Robust Generalization
Deepak Maurya, Adarsh Barik, Jean Honorio
Loss Function Adversarial Perturbation Plug and Play Robust Training Robust Framework

August 15, 2022

An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models
Brendon G. Anderson, Tanmay Gautam, Somayeh Sojoudi
Native Robustness Machine Learning Model Robust Training Robust Machine Learning

August 8, 2022

Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach
Saber Jafarpour, Alexander Davydov, Matthew Abate, Francesco Bullo, Samuel Coogan
Verification Task Robust Training Implicit Neural Network Non Euclidean Robustness Verification

July 22, 2022

Do Perceptually Aligned Gradients Imply Adversarial Robustness?
Roy Ganz, Bahjat Kawar, Michael Elad
Adversarial Attack Adversarial Training Adversarial Robustness Robust Training Gradient Alignment

July 21, 2022

Learning from Data with Noisy Labels Using Temporal Self-Ensemble
Jun Ho Lee, Jae Soon Baik, Tae Hwan Hwang, Jun Won Choi
LeArning Abstract Deep Neural Network Raw Data Noisy Label Robust Training Self Ensemble

July 9, 2022

Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
Taha Belkhouja, Yan Yan, Janardhan Rao Doppa
Theoretical Analysis Robust Training Robust Deep Novel Algorithm DNN Robustness Time Series Alignment

July 4, 2022

Removing Batch Normalization Boosts Adversarial Training
Haotao Wang, Aston Zhang, Shuai Zheng, Xingjian Shi, Mu Li, Zhangyang Wang
Adversarial Training Adversarial Robustness Batch Normalization Robust Training Normalizer Free

June 24, 2022

Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation
David B. Adrian, Andras Gabor Kupcsik, Markus Spies, Heiko Neumann
High Efficiency Robust Training Multi Object View Invariant Dense Object Descriptor

June 20, 2022

Understanding Robust Learning through the Lens of Representation Similarities
Christian Cianfarani, Arjun Nitin Bhagoji, Vikash Sehwag, Ben Y. Zhao, Prateek Mittal, Haitao Zheng
Representation Learning Camera Lens Robust Learning Robust Representation Robust Training Similar Representation DNN Robustness Robust Network

June 15, 2022

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
Jongwoo Ko, Bongsoo Yi, Se-Young Yun
Noisy Label Label Noise Robust Training Label Smoothing Auxiliary Classifier Lipschitz Regularization

June 13, 2022

Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
Gaoyuan Zhang, Songtao Lu, Yihua Zhang, Xiangyi Chen, Pin-Yu Chen, Quanfu Fan, Lee Martie, Lior Horesh, Mingyi Hong, Sijia Liu
Deep Neural Network Adversarial Attack Adversarial Training Adversarial Perturbation Visual Analogue Scale Robust Training

May 27, 2022

Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
Binghui Li, Jikai Jin, Han Zhong, John E. Hopcroft, Liwei Wang
Deep Learning Visual Perspective Robust Training Robust Generalization Expressive Power Robust Generalization Gap

May 26, 2022

An Analytic Framework for Robust Training of Artificial Neural Networks
Ramin Barati, Reza Safabakhsh, Mohammad Rahmati
Neural Network Adversarial Attack Adversarial Example Robust Learning Robust Model Robust Training

May 3, 2022

FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning
SangMook Kim, Wonyoung Shin, Soohyuk Jang, Hwanjun Song, Se-Young Yun
Native Robustness Noisy Label Robust Training Synthetic Benchmark Hop Neighbor

April 12, 2022

Toward Robust Spiking Neural Network Against Adversarial Perturbation
Ling Liang, Kaidi Xu, Xing Hu, Lei Deng, Yuan Xie
Native Robustness Adversarial Perturbation Spiking Neural Network Neuron Model Robust Training Robust SNN

March 31, 2022

Efficient Maximal Coding Rate Reduction by Variational Forms
Christina Baek, Ziyang Wu, Kwan Ho Ryan Chan, Tianjiao Ding, Yi Ma, Benjamin D. Haeffele
Robust Training Rate Reduction Variational Formulation