Global Robustness

Global robustness in machine learning focuses on developing models that maintain reliable performance even when faced with unexpected inputs or environmental changes, a crucial aspect for deploying AI in real-world applications. Current research emphasizes both improving the robustness of existing models, such as through federated learning and robust loss functions, and developing novel verification methods to certify global robustness guarantees, often employing techniques like mixed-integer programming and probabilistic approaches. This field is vital for ensuring the safety and reliability of AI systems across diverse domains, from manufacturing and autonomous driving to climate modeling and healthcare, where unpredictable conditions are common.

Papers

August 16, 2024

Enhancing Object Detection with Hybrid dataset in Manufacturing Environments: Comparing Federated Learning to Conventional Techniques
Vinit Hegiste, Snehal Walunj, Jibinraj Antony, Tatjana Legler, Martin Ruskowski
Object Detection Small Object Detection Current Method Robust Object Detection Global Robustness Manufacturing Environment Hybrid Data

August 2, 2024

Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition
Róisín Luo, James McDermott, Colm O'Riordan
Image Modeling Mechanistic Interpretability Global Interpretability Global Robustness Spectral Decomposition Perturbation Robustness

May 31, 2024

Certifying Global Robustness for Deep Neural Networks
You Li, Guannan Zhao, Shuyu Kong, Yunqi He, Hai Zhou
Deep Neural Network Robust Deep Global Robustness Local Robustness Robustness Measurement

February 29, 2024

Verification of Neural Networks' Global Robustness
Anan Kabaha, Dana Drachsler-Cohen
Neural Network Verification Task Global Robustness Local Robustness

September 24, 2023

DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning
Kangyang Luo, Shuai Wang, Yexuan Fu, Xiang Li, Yunshi Lan, Ming Gao
Heterogeneous Federated Learning Decentralized Data Data Free Knowledge Distillation Global Robustness

September 4, 2023

Expanding Mars Climate Modeling: Interpretable Machine Learning for Modeling MSL Relative Humidity
Nour Abdelmoneim, Dattaraj B. Dhuri, Dimitra Atri, Germán Martínez
Interpretable Machine Learning Earth System Model Global Robustness Martian Terrain

June 21, 2023

Verifying Global Neural Network Specifications using Hyperproperties
David Boetius, Stefan Leue
Neural Network Global Robustness Order Hyperproperties

April 20, 2023

Using Z3 for Formal Modeling and Verification of FNN Global Robustness
Yihao Zhang, Zeming Wei, Xiyue Zhang, Meng Sun
Adversarial Robustness Verification Task Formal Model Global Deep Global Robustness DNN Robustness Adversarial Region

April 19, 2023

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
Zaitang Li, Pin-Yu Chen, Tsung-Yi Ho
Adversarial Attack Generative Model Generative Adversarial Network Adversarial Robustness Adversarial Perturbation Human Score Global Robustness

January 5, 2023

gRoMA: a Tool for Measuring the Global Robustness of Deep Neural Networks
Natan Levy, Raz Yerushalmi, Guy Katz
Deep Neural Network BRIO Tool Adversarial Input Global Robustness

December 1, 2022

Bayesian Heuristics for Robust Spatial Perception
Aamir Hussain Chughtai, Muhammad Tahir, Momin Uppal
Computer Vision Point Cloud Registration Simple Heuristic Robust Perception Global Robustness Heuristic Estimate Simultaneous Estimation

November 18, 2022

Global quantitative robustness of regression feed-forward neural networks
Tino Werner
Neural Network Novel Regression Regression Task Robust Regression Robust Loss Function Global Robustness

August 16, 2022

Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusion
Duy Phuong Nguyen, Sixing Yu, J. Pablo Muñoz, Ali Jannesari
Knowledge Distillation Heterogeneous Federated Learning Knowledge Extraction Edge Model Global Robustness Multi modEl Fusion Specific Model

August 15, 2022

A Tool for Neural Network Global Robustness Certification and Training
Zhilu Wang, Yixuan Wang, Feisi Fu, Ruochen Jiao, Chao Huang, Wenchao Li, Qi Zhu
Training Data BRIO Tool Robustness Certification Global Robustness State of the Art Robustness

March 26, 2022

Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding
Zhilu Wang, Chao Huang, Qi Zhu
Neural Network Robustness Certification Global Robustness Local Robustness Multi Encoder

March 1, 2022

A Domain-Theoretic Framework for Robustness Analysis of Neural Networks
Can Zhou, Razin A. Shaikh, Yiran Li, Amin Farjudian
Neural Network Differentiable Neural Domain Model Robustness Analysis Global Robustness Local Robustness