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

November 18, 2022

A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
Guanqin Zhang, Jiankun Sun, Feng Xu, H. M. N. Dilum Bandara, Shiping Chen, Yulei Sui, Tim Menzies
Deep Learning Deep Neural Network Native Robustness Raw Data Urban Environment DNN Model Robust Deep Cautionary TALE DNN Robustness Parameter Configuration

November 14, 2022

Stability and Robustness of Distributed Suboptimal Model Predictive Control
Giuseppe Belgioioso, Dominic Liao-McPherson, Mathias Hudoba de Badyn, Nicolas Pelzmann, John Lygeros, Florian Dörfler
Native Robustness Core Stability Model Predictive Control Large Scale Optimization

November 13, 2022

Certifying Robustness of Convolutional Neural Networks with Tight Linear Approximation
Yuan Xiao, Tongtong Bai, Mingzheng Gu, Chunrong Fang, Zhenyu Chen
Convolutional Neural Network Native Robustness State of the Art Robustness Verification Tight Approximation Robustness Bound

November 12, 2022

Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement
Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk
Native Robustness Data Augmentation Robust Representation Self Supervised Speech Representation Noisy Environment Multi Task Fusion Edge Speech Application

November 11, 2022

On the robustness of non-intrusive speech quality model by adversarial examples
Hsin-Yi Lin, Huan-Hsin Tseng, Yu Tsao
Native Robustness Adversarial Example Adversarial Training Adversarial Perturbation Auditory Perception Non Intrusive Speech Speech Quality Prediction

November 10, 2022

November 9, 2022

On the Robustness of Explanations of Deep Neural Network Models: A Survey
Amlan Jyoti, Karthik Balaji Ganesh, Manoj Gayala, Nandita Lakshmi Tunuguntla, Sandesh Kamath, Vineeth N Balasubramanian
Deep Neural Network Timely Survey Native Robustness Line by Line Explanation High Explainability Explainability Method Robust Explanation Attribution Attack

November 8, 2022

Parameter and Data Efficient Continual Pre-training for Robustness to Dialectal Variance in Arabic
Soumajyoti Sarkar, Kaixiang Lin, Sailik Sengupta, Leonard Lausen, Sheng Zha, Saab Mansour
Language Model Native Robustness Multilingual Model Many Parameter Monolingual Model Arabic Speaker Arabic Dataset Language Modeling Loss

November 4, 2022

Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions
Gaurav Verma, Vishwa Vinay, Ryan A. Rossi, Srijan Kumar
Native Robustness Multimodal Phenomenon Multimodal Learning Multimodal Deep Learning Multimodal Classification

November 2, 2022

Native Robustness

Papers

A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning

Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality

Differentially Private Optimizers Can Learn Adversarially Robust Models

Efficiently Finding Adversarial Examples with DNN Preprocessing

Stability and Robustness of Distributed Suboptimal Model Predictive Control

Certifying Robustness of Convolutional Neural Networks with Tight Linear Approximation

Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement

On the robustness of non-intrusive speech quality model by adversarial examples

Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses

Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness

Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity

MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions

Impact of Adversarial Training on Robustness and Generalizability of Language Models

On the Robustness of Explanations of Deep Neural Network Models: A Survey

Parameter and Data Efficient Continual Pre-training for Robustness to Dialectal Variance in Arabic

Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions

Isometric Representations in Neural Networks Improve Robustness

Investigating the robustness of a learning-based method for quantitative phase retrieval from propagation-based x-ray phase contrast measurements under laboratory conditions

Causal Counterfactuals for Improving the Robustness of Reinforcement Learning

Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise