Adversarial Risk

Adversarial risk focuses on the vulnerability of machine learning models to malicious inputs designed to cause misclassification or other undesirable outputs. Current research investigates various attack methods, including test-time data poisoning and attacks targeting specific model components (e.g., face detectors, language models), and explores defense strategies such as adversarial training, robust model architectures (e.g., Vision Transformers), and novel loss functions. Understanding and mitigating adversarial risk is crucial for deploying reliable machine learning systems in security-sensitive applications, driving ongoing efforts to develop more robust models and rigorous evaluation methods.

Papers

January 29, 2023

Uncovering Adversarial Risks of Test-Time Adaptation
Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal
Test Time Adaptation Adversarial Risk Time Adaptation Malicious Sample

January 9, 2023

On adversarial robustness and the use of Wasserstein ascent-descent dynamics to enforce it
Camilo Garcia Trillos, Nicolas Garcia Trillos
Adversarial Robustness Greater Public Use Mean Field Wasserstein Gradient Flow Adversarial Risk Learning Problem Mean Field Limit

December 5, 2022

Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
Bao Gia Doan, Ehsan Abbasnejad, Javen Qinfeng Shi, Damith C. Ranasinghe
Adversarial Attack Adversarial Training Bayesian Neural Network High Quality Risk Description Bayesian Learning Information Gain Adversarial Risk Robust Adversarial

August 4, 2022

Conformal Risk Control
Anastasios N. Angelopoulos, Stephen Bates, Adam Fisch, Lihua Lei, Tal Schuster
Conformal Prediction Convex Loss Adversarial Risk Risk Management Conformal Risk Control

July 8, 2022

A law of adversarial risk, interpolation, and label noise
Daniel Paleka, Amartya Sanyal
Label Noise Legal Text Interpolation Regime Adversarial Vulnerability Adversarial Risk

June 18, 2022

April 28, 2022

Formulating Robustness Against Unforeseen Attacks
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Native Robustness Adversarial Example Adversarial Training Generalization Gap Adversarial Risk

April 27, 2022

The Multimarginal Optimal Transport Formulation of Adversarial Multiclass Classification
Nicolas Garcia Trillos, Matt Jacobs, Jakwang Kim
Generative Adversarial Adversarial Risk Learning Problem Multi Marginal Optimal Transport Optimal Adversarial Barycenter Driven Localization

April 14, 2022

Q-TART: Quickly Training for Adversarial Robustness and in-Transferability
Madan Ravi Ganesh, Salimeh Yasaei Sekeh, Jason J. Corso
Adversarial Robustness Task Transferability Adversarial DEfense Faster Training Adversarial Risk

March 24, 2022

A Manifold View of Adversarial Risk
Wenjia Zhang, Yikai Zhang, Xiaoling Hu, Mayank Goswami, Chao Chen, Dimitris Metaxas
Adversarial Risk Flamelet Generated Manifold Manifold Adversarial

January 22, 2022

The Many Faces of Adversarial Risk
Muni Sreenivas Pydi, Varun Jog
Adversarial Robustness Adversarial Risk Unbalanced Optimal Transport Wasserstein Uncertainty

December 31, 2021

Benign Overfitting in Adversarially Robust Linear Classification
Jinghui Chen, Yuan Cao, Quanquan Gu
Adversarial Example Adversarial Training Adversarial Perturbation Benign Overfitting Adversarial Risk Robust Classification

November 9, 2021

Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
Pengfei Xia, Ziqiang Li, Bin Li
Native Robustness Adversarial Example Loss Function Adversarial Robustness Adversarial Risk Approximation Error