Robust Machine Learning

Robust machine learning aims to develop models that reliably perform under various conditions, including noisy data, adversarial attacks, and distribution shifts. Current research focuses on improving model robustness through techniques like data abstraction, uncertainty quantification (used for explainability and rejection of untrustworthy predictions), and novel algorithms such as coevolutionary approaches for decision trees and minimax regret optimization. These advancements are crucial for deploying machine learning in safety-critical applications and improving the trustworthiness and reliability of AI systems across diverse domains, from healthcare to 5G network optimization.

Papers

July 11, 2024

How to beat a Bayesian adversary
Zihan Ding, Kexin Jin, Jonas Latz, Chenguang Liu
Adversarial Attack Gradient Flow Robust Machine Learning Multiple Adversary

June 12, 2024

Improving Noise Robustness through Abstractions and its Impact on Machine Learning
Alfredo Ibias, Karol Capala, Varun Ravi Varma, Anna Drozdz, Jose Sousa
Machine Learning Adversarial Attack Native Robustness Global Impact Metric Aware Abstraction Noise Robustness Robust Machine Learning

March 15, 2024

Explainability through uncertainty: Trustworthy decision-making with neural networks
Arthur Thuy, Dries F. Benoit
Neural Network High Explainability High Uncertainty Anticipation Uncertainty Estimation Robust Machine Learning

December 14, 2023

Coevolutionary Algorithm for Building Robust Decision Trees under Minimax Regret
Adam Żychowski, Andrew Perrault, Jacek Mańdziuk
Adversarial Attack Minimax Regret Coevolutionary Algorithm Adaptive Coevolution Robust Machine Learning

October 8, 2023

Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications
Azim Akhtarshenas, Mohammad Ali Vahedifar, Navid Ayoobi, Behrouz Maham, Tohid Alizadeh, Sina Ebrahimi, David López-Pérez
Machine Learning Model Financial Application Comprehensive Survey Recent Advance Model Training Robust Machine Learning

October 2, 2023

A Robust Machine Learning Approach for Path Loss Prediction in 5G Networks with Nested Cross Validation
Ibrahim Yazıcı, Emre Gures
Machine Learning G Network Support Vector Regression Path Loss Robust Machine Learning

August 8, 2023

Comprehensive Assessment of the Performance of Deep Learning Classifiers Reveals a Surprising Lack of Robustness
Michael W. Spratling
Native Robustness System Performance Comprehensive Evaluation Robustness Evaluation Robust Evaluation Deep Learning Classifier Benchmark Score Robust Machine Learning Lack Thereof State of the Art Robustness

June 19, 2023

AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator
Elysia Q. Smyers, Sydney M. Katz, Anthony L. Corso, Mykel J. Kochenderfer
Collision Avoidance Interactive Simulation Autonomous Flight Object Detection Benchmark Robust Machine Learning Based Obstacle Avoidance

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

July 3, 2022

Identifying the Context Shift between Test Benchmarks and Production Data
Matthew Groh
Benchmark Datasets Dataset Shift Robust Machine Learning High Quality Benchmark Production Data Dynamic Benchmark Context Shift

February 18, 2022

Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem
Abderrahmen Amich, Birhanu Eshete
Native Robustness Adversarial Example Adversarial Input Tiltable Link Robust Machine Learning Machine Learning Robustness

February 11, 2022

Minimax Regret Optimization for Robust Machine Learning under Distribution Shift
Alekh Agarwal, Tong Zhang
Distribution Shift Regret Bound Distributionally Robust Optimization Robust Machine Learning

January 12, 2022

RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems
Zohreh Ovaisi, Shelby Heinecke, Jia Li, Yongfeng Zhang, Elena Zheleva, Caiming Xiong
Native Robustness Recommender System Robustness Evaluation Easy to Use Toolkit Robustness Analysis Recommender Model Robust Machine Learning

November 15, 2021

SPLDExtraTrees: Robust machine learning approach for predicting kinase inhibitor resistance
Ziyi Yang, Zhaofeng Ye, Yijia Xiao, Changyu Hsieh, Shengyu Zhang
Robust Machine Learning Protein Ligand Binding Drug Resistance

Robust Machine Learning

Papers

How to beat a Bayesian adversary

Improving Noise Robustness through Abstractions and its Impact on Machine Learning

Explainability through uncertainty: Trustworthy decision-making with neural networks

Coevolutionary Algorithm for Building Robust Decision Trees under Minimax Regret

Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications

A Robust Machine Learning Approach for Path Loss Prediction in 5G Networks with Nested Cross Validation

Comprehensive Assessment of the Performance of Deep Learning Classifiers Reveals a Surprising Lack of Robustness

AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator

An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models

Identifying the Context Shift between Test Benchmarks and Production Data

Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem

Minimax Regret Optimization for Robust Machine Learning under Distribution Shift

RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems

SPLDExtraTrees: Robust machine learning approach for predicting kinase inhibitor resistance