Robust Model

Robust model research aims to create machine learning models that maintain high performance despite variations in input data, including adversarial attacks and distribution shifts. Current efforts focus on developing training methods that enhance robustness across multiple perturbation types (e.g., multi-norm training), leveraging self-supervised learning for improved feature representation, and exploring the role of pre-training and data balancing in mitigating bias and improving generalization. These advancements are crucial for deploying reliable machine learning systems in real-world applications, particularly in safety-critical domains like healthcare and autonomous driving, where model robustness is paramount.

Papers

October 3, 2023

AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework
Xilie Xu, Jingfeng Zhang, Mohan Kankanhalli
Adversarial Robustness Robust Model Feature Extractor Robust Fine Tuning Adversarial Objective

September 28, 2023

On the Trade-offs between Adversarial Robustness and Actionable Explanations
Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju
Machine Learning Model Adversarial Robustness Model Robustness Robust Model Robust Linear

August 21, 2023

Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models
Peiyan Zhang, Haoyang Liu, Chaozhuo Li, Xing Xie, Sunghun Kim, Haohan Wang
Native Robustness Image Datasets Flawed Foundation Robust Model Robustness Evaluation Robustness Measurement

July 23, 2023

Robust explicit model predictive control for hybrid linear systems with parameter uncertainties
Oleg Balakhnov, Sergei Savin, Alexandr Klimchik
Predictive Control Model Predictive Control Robust Model Parameter Uncertainty Hybrid System Polynomial Zonotopes

July 4, 2023

Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability Connection
Delyan Boychev
Adversarial Attack Native Robustness Adversarial Training Inherent Interpretability Robust Model Robust Interpretation Interpretable Computer Vision

June 27, 2023

RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music
Haojie Wei, Xueke Cao, Tangpeng Dan, Yueguo Chen
Robust Model Audio Processing Music Source Separation Pitch Estimation

June 22, 2023

Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models
Francesco Croce, Naman D Singh, Matthias Hein
Adversarial Attack Semantic Segmentation Adversarial Training Semantic Segmentation Model Robust Model Faster Training Robust Segmentation Robust Semantic Segmentation

June 1, 2023

Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review
Mathias Lundteigen Mohus, Jinyue Li
Adversarial Attack Native Robustness Adversarial Robustness Unsupervised Learning Systematic Review Robust Model Unsupervised Model Unsupervised Machine Learning

May 18, 2023

NODE-ImgNet: a PDE-informed effective and robust model for image denoising
Xinheng Xie, Yue Wu, Hao Ni, Cuiyu He
Convolutional Neural Network Neural Ordinary Differential Equation Image Denoising Robust Model Noisy Image

March 22, 2023

TsSHAP: Robust model agnostic feature-based explainability for time series forecasting
Vikas C. Raykar, Arindam Jati, Sumanta Mukherjee, Nupur Aggarwal, Kanthi Sarpatwar, Giridhar Ganapavarapu, Roman Vaculin
High Explainability Time Series Forecasting Black Box Robust Model Interpretable Feature Model Agnostic Explainability

March 21, 2023

Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation
Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Pinxue Guo, Kaixun Jiang, Wenqiang Zhang, Lizhe Qi
Adversarial Training Adversarial Robustness Robust Model Thin Air Adversarial Robustness Distillation

March 15, 2023

EvalAttAI: A Holistic Approach to Evaluating Attribution Maps in Robust and Non-Robust Models
Ian E. Nielsen, Ravi P. Ramachandran, Nidhal Bouaynaya, Hassan M. Fathallah-Shaykh, Ghulam Rasool
Robust Version Attribution Method Robust Model Holistic Approach Attribution Map

March 5, 2023

Robustness, Evaluation and Adaptation of Machine Learning Models in the Wild
Vihari Piratla
Native Robustness Machine Learning Model Global Evaluation Domain Shift Wild Challenge Adaptation Concern Robust Model Multi Domain Training

March 1, 2023

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
Jianing Zhu, Jiangchao Yao, Tongliang Liu, Quanming Yao, Jianliang Xu, Bo Han
Adversarial Training Robust Model Adversarial Data Robustness Problem Federated Adversarial

February 24, 2023

Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
Ruisi Cai, Zhenyu Zhang, Zhangyang Wang
Native Robustness Model Robustness Patch Based Robust Model Weight Freezing General Robustness

February 19, 2023

Stationary Point Losses for Robust Model
Weiwei Gao, Dazhi Zhang, Yao Li, Zhichang Guo, Ovanes Petrosian
Adversarial Attack Native Robustness Adversarial Example Cross Entropy Robust Model Loss Design Boundary Localization

February 6, 2023

Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust
Leonid Erlygin, Vladimir Zholobov, Valeriia Baklanova, Evgeny Sokolovskiy, Alexey Zaytsev
Gaussian Process Time Series Forecasting Uncertainty Estimation Surrogate Model Robust Model Accurate Uncertainty

January 31, 2023

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
Meyer Scetbon, Elvis Dohmatob
Adversarial Attack Native Robustness Robust Model Robust Regression Early Stopping Adversarial Risk

January 30, 2023

Robust Meta Learning for Image based tasks
Penghao Jiang, Xin Ke, ZiFeng Wang, Chunxi Li
Machine Learning Model Generalization Performance New Task Robust Model Robust Meta Learning

January 28, 2023

Learning Optimal Features via Partial Invariance
Moulik Choraria, Ibtihal Ferwana, Ankur Mani, Lav R. Varshney
Feature Selection Robust Model Learning Model Invariant Risk Minimization Invariant Model