Robustness Certificate

Robustness certificates aim to provide mathematically provable guarantees about the resilience of machine learning models, particularly deep neural networks, to adversarial attacks or noisy inputs. Current research heavily focuses on improving the accuracy and efficiency of methods like randomized smoothing, often employing techniques such as self-ensembling or surrogate models to enhance certification speed and robustness radius. These advancements are crucial for deploying reliable AI systems in safety-critical applications, where confidence in model predictions under uncertainty is paramount, and for furthering our theoretical understanding of model vulnerability.

Papers

September 20, 2024

Certified Adversarial Robustness via Partition-based Randomized Smoothing
Hossein Goli, Farzan Farnia
Gaussian Noise Randomized Smoothing Robustness Certificate Robustness Radius

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 Self Ensemble Robustness Radius \Ell_p$ Robustness

April 26, 2024

Estimating the Robustness Radius for Randomized Smoothing with 100$\times$ Sample Efficiency
Emmanouil Seferis, Stefanos Kollias, Chih-Hong Cheng
Native Robustness Sample Efficiency Randomized Smoothing Robustness Certificate Robustness Radius

February 12, 2024

Accelerated Smoothing: A Scalable Approach to Randomized Smoothing
Devansh Bhardwaj, Kshitiz Kaushik, Sarthak Gupta
Adversarial Attack Randomized Smoothing Scalable Approach Smoothed Classifier Robustness Certificate Smoothing Algorithm Surrogate Neural Network

November 3, 2023

Safe Online Dynamics Learning with Initially Unknown Models and Infeasible Safety Certificates
Alexandre Capone, Ryan Cosner, Aaron Ames, Sandra Hirche
Control Barrier Function Safety Critical Control Robustness Certificate Safety Certificate

August 17, 2023

General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing
Dmitrii Korzh, Mikhail Pautov, Olga Tsymboi, Ivan Oseledets
Native Robustness Randomized Smoothing Left Corner Transformation Preserving Transformation Robustness Certificate Canonical Lipschitz Mechanism Lipschitz Continuity

June 25, 2023

Computational Asymmetries in Robust Classification
Samuele Marro, Michele Lombardi
Adversarial Attack Native Robustness Adversarial Robustness Information Asymmetry Robust Classification Robustness Certification Robustness Certificate

June 20, 2023

Structure-Aware Robustness Certificates for Graph Classification
Pierre Osselin, Henry Kenlay, Xiaowen Dong
Native Robustness Graph Classification Robustness Certificate Certificate Synthesis

May 31, 2023

Incremental Randomized Smoothing Certification
Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh, Sasa Misailovic
Robustness Guarantee Robustness Certification Smoothed Classifier Robustness Certificate

March 28, 2023

Provable Robustness for Streaming Models with a Sliding Window
Aounon Kumar, Vinu Sankar Sadasivan, Soheil Feizi
Machine Learning Adversarial Perturbation Sliding Window Streaming Model Robustness Certificate Independent Sampling

February 9, 2023

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
Andrew C. Cullen, Shijie Liu, Paul Montague, Sarah M. Erfani, Benjamin I. P. Rubinstein
Adversarial Example Attack Performance DNN Robustness Robustness Certificate

January 31, 2023

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
Zhuoqun Huang, Neil G. Marchant, Keane Lucas, Lujo Bauer, Olga Ohrimenko, Benjamin I. P. Rubinstein
Adversarial Example Randomized Smoothing Robustness Certificate Sequence Classifier Deletion Inference Adversarial Removal

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 25, 2021

Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity
Bernardo Aquino, Arash Rahnama, Peter Seiler, Lizhen Lin, Vijay Gupta
Neural Network Adversarial Attack Native Robustness Adversarial Example Local Non Dissipativity Robustness Certificate

Robustness Certificate

Papers

Certified Adversarial Robustness via Partition-based Randomized Smoothing

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

Estimating the Robustness Radius for Randomized Smoothing with 100$\times$ Sample Efficiency

Accelerated Smoothing: A Scalable Approach to Randomized Smoothing

Safe Online Dynamics Learning with Initially Unknown Models and Infeasible Safety Certificates

General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing

Computational Asymmetries in Robust Classification

Structure-Aware Robustness Certificates for Graph Classification

Incremental Randomized Smoothing Certification

Provable Robustness for Streaming Models with a Sliding Window

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

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

Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity