Robustness Trade

Robustness trade-off research explores the inherent tension between a model's accuracy on standard data and its resilience to adversarial attacks or distributional shifts. Current efforts focus on developing algorithms and training techniques, such as adversarial training, sharpness-aware minimization, and novel loss functions, to optimize this trade-off across various model architectures, including neural networks and ranking models, often within federated learning frameworks. This research is crucial for deploying reliable machine learning systems in real-world applications where robustness to noise, uncertainty, and malicious inputs is paramount, impacting fields ranging from cybersecurity to healthcare.

Papers

August 7, 2024

Overcoming Brittleness in Pareto-Optimal Learning-Augmented Algorithms
Spyros Angelopoulos, Christoph Dürr, Alex Elenter, Yanni Lefki
Pareto Optimal Online Algorithm Optimal Trade Learning Augmented Algorithm Brittle Fracture Robustness Trade

April 16, 2024

Do Counterfactual Examples Complicate Adversarial Training?
Eric Yeats, Cameron Darwin, Eduardo Ortega, Frank Liu, Hai Li
Robust Model Robust Classifier Counterfactual Example Non Robust Feature Counterfactual Generative Robustness Trade

February 9, 2024

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
Enyi Jiang, Gagandeep Singh
Adversarial Attack Adversarial Training Adversarial Robustness \Ell_p$ Norm Norm Attack Robustness Trade

January 26, 2024

Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
Shruthi Gowda, Bahram Zonooz, Elahe Arani
Adversarial Attack Adversarial Training Robust Generalization Adversarial Setting Robustness Trade

December 16, 2023

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off
Yu-An Liu, Ruqing Zhang, Mingkun Zhang, Wei Chen, Maarten de Rijke, Jiafeng Guo, Xueqi Cheng
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial DEfense Neural Ranker Robustness Trade

October 6, 2023

Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning
Liam Collins, Shanshan Wu, Sewoong Oh, Khe Chai Sim
Native Robustness Fine Tuning Foundation Model Federated Prompt Robustness Trade

July 25, 2023

Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis
Yang Jiao, Kai Yang, Dongjin Song
Native Robustness General Analysis Practical Algorithm Robust Optimization Distributionally Robust Optimization Non Convex Objective Robustness Trade

May 9, 2023

Sharpness-Aware Minimization Alone can Improve Adversarial Robustness
Zeming Wei, Jingyu Zhu, Yihao Zhang
Adversarial Training Adversarial Robustness Sharpness Aware Minimization Robustness Trade

April 11, 2023

The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
Lu Han, Han-Jia Ye, De-Chuan Zhan
Multivariate Time Series Multivariate Time Series Forecasting Multivariate Time Series Data Forecasting Model Capacity Loss Multivariate Forecasting Robustness Trade

October 14, 2022

Distributed Distributionally Robust Optimization with Non-Convex Objectives
Yang Jiao, Kai Yang, Dongjin Song
Robust Optimization Distributionally Robust Optimization Non Convex Objective Robustness Trade Active SEt

April 19, 2022

Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks
Kenneth T. Co, David Martinez-Rego, Zhongyuan Hau, Emil C. Lupu
Adversarial Attack Robustness Trade Jacobian Regularization

Robustness Trade

Papers

Overcoming Brittleness in Pareto-Optimal Learning-Augmented Algorithms

Do Counterfactual Examples Complicate Adversarial Training?

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness

Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning

Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis

Sharpness-Aware Minimization Alone can Improve Adversarial Robustness

The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting

Distributed Distributionally Robust Optimization with Non-Convex Objectives

Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks