Robustness Testing

Robustness testing evaluates the reliability of machine learning models, particularly deep learning systems, under various unexpected conditions or perturbations. Current research focuses on assessing robustness across diverse applications, including medical image analysis, assistive robotics, multi-agent systems, and cyber-physical systems, employing techniques like test-time augmentation and adversarial attacks to probe model vulnerabilities. These efforts are crucial for ensuring the safe and dependable deployment of AI in high-stakes domains, improving model trustworthiness and ultimately advancing the reliability of AI-driven technologies.

Papers

June 27, 2024

Robustness Testing of Black-Box Models Against CT Degradation Through Test-Time Augmentation
Jack Highton, Quok Zong Chong, Samuel Finestone, Arian Beqiri, Julia A. Schnabel, Kanwal K. Bhatia
Native Robustness Deep Learning Model Medical Image Segmentation Image Quality Black Box Model Image Degradation Test Time Augmentation Robustness Testing

June 18, 2024

Robustness Testing of Multi-Modal Models in Varied Home Environments for Assistive Robots
Lea Hirlimann, Shengqiang Zhang, Hinrich Schütze, Philipp Wicke
Multi Modality Multi Modal Model Assistive Robot Elderly People Robot Model General Environment Robustness Testing

June 9, 2023

Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents
Ziyuan Zhou, Guanjun Liu
Multi Agent Reinforcement Learning Adversarial Perturbation Critical Agent State Perturbation Robustness Testing

September 29, 2022

Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition
Jonathan Kamp, Lisa Beinborn, Antske Fokkens
Language Model Additive Perturbation Sub Population Robustness Testing Argument Structure

May 17, 2022

Hierarchical Distribution-Aware Testing of Deep Learning
Wei Huang, Xingyu Zhao, Alec Banks, Victoria Cox, Xiaowei Huang
Deep Learning Adversarial Example Adversarial Robustness Adversarial Perturbation Local Robustness Test Label Distribution Robustness Testing

April 20, 2022

Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems
Xugui Zhou, Maxfield Kouzel, Homa Alemzadeh
Machine Learning Native Robustness Raw Data Cyber Physical System Based Anomaly Detection Robustness Test Robustness Testing

Robustness Testing

Papers

Robustness Testing of Black-Box Models Against CT Degradation Through Test-Time Augmentation

Robustness Testing of Multi-Modal Models in Varied Home Environments for Assistive Robots

Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents

Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition

Hierarchical Distribution-Aware Testing of Deep Learning

Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems