Native Robustness

Native robustness in machine learning focuses on developing models inherently resistant to various forms of input perturbations, including adversarial attacks and noisy data, without relying solely on post-hoc defenses. Current research emphasizes techniques like ensemble methods, reprogramming existing models, and modifying training procedures (e.g., using different learning rates for specific model layers or incorporating regularization methods) to improve robustness across diverse model architectures, including convolutional neural networks, vision transformers, and large language models. This field is crucial for deploying reliable AI systems in safety-critical applications, such as healthcare and autonomous driving, where model resilience to unexpected inputs is paramount.

Papers

August 1, 2022

Assessing the robustness of critical behavior in stochastic cellular automata
Sidney Pontes-Filho, Pedro Lind, Stefano Nichele
Native Robustness Critical Scenario Criticality Ordered Spin Sequence

July 31, 2022

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization
Sein Park, Yeongsang Jang, Eunhyeok Park
Native Robustness Post Training Quantization Quantization Aware Training Quantization Error Saturation Effect Learned Symmetry Quantization Robust Parameter

July 27, 2022

On the robustness of self-supervised representations for multi-view object classification
David Torpey, Richard Klein
Native Robustness Self Supervised Multi View Self Supervised Pre Training Object Centric Better Representation

July 24, 2022

Can we achieve robustness from data alone?
Nikolaos Tsilivis, Jingtong Su, Julia Kempe
Adversarial Attack Native Robustness Raw Data Meta Learning Robust Classification Standard Gradient Descent

July 23, 2022

Testing the Robustness of Learned Index Structures
Matthias Bachfischer, Renata Borovica-Gajic, Benjamin I. P. Rubinstein
Native Robustness Worst Case Deep Learning Workload Learned Index

July 22, 2022

Provable Defense Against Geometric Transformations
Rem Yang, Jacob Laurel, Sasa Misailovic, Gagandeep Singh
Native Robustness Image Transformation Geometric Transformation Provable Defense Spatial Verification

July 21, 2022

AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance
Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie
Native Robustness Adversarial Robustness Generalization Performance Training Method Data Processing Double Robustness

July 20, 2022

On the Robustness of 3D Object Detectors
Fatima Albreiki, Sultan Abughazal, Jean Lahoud, Rao Anwer, Hisham Cholakkal, Fahad Khan
Native Robustness 3D Object Detection 3D Object 3D Object Detector

July 18, 2022

July 16, 2022

Progress and limitations of deep networks to recognize objects in unusual poses
Amro Abbas, Stéphane Deny
Convolutional Neural Network Native Robustness Deep Network Arbitrary Object Fundamental Limitation Much Progress Noise Robust Learning Unusual Pose

July 13, 2022

July 11, 2022

How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies
Edward Small, Wei Shao, Zeliang Zhang, Peihan Liu, Jeffrey Chan, Kacper Sokol, Flora Salim
Native Robustness Fairness Evaluation Fair Model Fairness Method Robustness Measurement Fairness Benchmark Datasets

July 9, 2022

On the Robustness and Anomaly Detection of Sparse Neural Networks
Morgane Ayle, Bertrand Charpentier, John Rachwan, Daniel Zügner, Simon Geisler, Stephan Günnemann
Native Robustness Anomaly Detection Structured Sparsity Sparse Neural Network Sparse Subnetworks Robustness Problem

July 8, 2022

July 7, 2022

July 5, 2022

PRoA: A Probabilistic Robustness Assessment against Functional Perturbations
Tianle Zhang, Wenjie Ruan, Jonathan E. Fieldsend
Native Robustness Small Perturbation Neural Network Robustness Probabilistic Robustness

Native Robustness

Papers

Assessing the robustness of critical behavior in stochastic cellular automata

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

On the robustness of self-supervised representations for multi-view object classification

Can we achieve robustness from data alone?

Testing the Robustness of Learned Index Structures

Provable Defense Against Geometric Transformations

AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance

On the Robustness of 3D Object Detectors

Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning

Benchmarking Machine Learning Robustness in Covid-19 Genome Sequence Classification

Progress and limitations of deep networks to recognize objects in unusual poses

On the Robustness of Bayesian Neural Networks to Adversarial Attacks

Probing the Robustness of Independent Mechanism Analysis for Representation Learning

How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies

On the Robustness and Anomaly Detection of Sparse Neural Networks

How many perturbations break this model? Evaluating robustness beyond adversarial accuracy

Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks

Robust Watermarking for Video Forgery Detection with Improved Imperceptibility and Robustness

On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Network

PRoA: A Probabilistic Robustness Assessment against Functional Perturbations