\Ell_p$ Robustness

$\ell_p$ robustness in machine learning focuses on developing models resistant to adversarial attacks that perturb inputs within an $\ell_p$ ball. Current research emphasizes methods like randomized smoothing and its variants, exploring techniques to improve certified robustness guarantees (provable lower bounds on the size of tolerable perturbations) and address the computational challenges posed by high-dimensional data. This field is crucial for deploying machine learning models in safety-critical applications, as certified robustness provides a measure of confidence in model predictions against malicious or noisy inputs. The development of more efficient and effective certification methods remains a key area of ongoing investigation.

Papers

September 4, 2024

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble
Chang Dong, Zhengyang Li, Liangwei Zheng, Weitong Chen, Wei Emma Zhang
Native Robustness Adversarial Robustness Time Series Classification Randomized Smoothing Robustness Certificate Robustness Radius Self Ensemble \Ell_p$ Robustness

April 15, 2024

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
Song Xia, Yi Yu, Xudong Jiang, Henghui Ding
Data Dimensionality Randomized Smoothing Reversal Curse Dual System Certified Robustness Robustness Radius \Ell_p$ Robustness

October 13, 2023

Is Certifying $\ell_p$ Robustness Still Worthwhile?
Ravi Mangal, Klas Leino, Zifan Wang, Kai Hu, Weicheng Yu, Corina Pasareanu, Anupam Datta, Matt Fredrikson
Adversarial Attack Threat Model Robustness Certification Certified Robustness Worth Multiple Word Norm Attack \Ell_p$ Robustness

March 17, 2023

Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified $\ell_p$ Attacks
Ren Wang, Yuxuan Li, Sijia Liu
Adversarial Attack Adversarial Robustness Adversarial DEfense Neural Network Robustness Norm Attack \Ell_p$ Robustness

July 14, 2022

Provably Adversarially Robust Nearest Prototype Classifiers
Václav Voráček, Matthias Hein
Adversarial Perturbation Threat Model Prototype Classifier Prototype Aggregation \Ell_p$ Robustness

March 16, 2022

Provable Adversarial Robustness for Fractional Lp Threat Models
Alexander Levine, Soheil Feizi
Adversarial Attack Adversarial Robustness Threat Model Learning Norm \Ell_p$ Robustness

December 10, 2021

Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach
Saber Jafarpour, Matthew Abate, Alexander Davydov, Francesco Bullo, Samuel Coogan
Adversarial Robustness Implicit Neural Network Robustness Verification Robustness Certificate \Ell_p$ Robustness

November 17, 2021

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee, Doguk Kim, Jinwoo Shin
Training Data Adversarial Perturbation Certified Robustness Smoothed Classifier \Ell_p$ Robustness

\Ell_p$ Robustness

Papers

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Is Certifying $\ell_p$ Robustness Still Worthwhile?

Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified $\ell_p$ Attacks

Provably Adversarially Robust Nearest Prototype Classifiers

Provable Adversarial Robustness for Fractional Lp Threat Models

Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness