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

January 21, 2024

Enhance Eye Disease Detection using Learnable Probabilistic Discrete Latents in Machine Learning Architectures
Anirudh Prabhakaran, YeKun Xiao, Ching-Yu Cheng, Dianbo Liu
Native Robustness Machine Learning Model Fundus Image Generative Flow Network Discrete Latent Eye Disease Ophthalmic Image Dropout Mask

January 19, 2024

FIMBA: Evaluating the Robustness of AI in Genomics via Feature Importance Adversarial Attacks
Heorhii Skovorodnikov, Hoda Alkhzaimi
Artificial Intelligence Adversarial Attack Native Robustness Artificial Intelligence Model Adversarial Sample Variational AutoEncoder

January 17, 2024

January 16, 2024

January 15, 2024

Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes
Shayan Mohajer Hamidi, Linfeng Ye
Adversarial Attack Native Robustness Adversarial Robustness DNN Robustness Adversarial Polytope

January 11, 2024

Surrogate Neural Networks Local Stability for Aircraft Predictive Maintenance
Mélanie Ducoffe, Guillaume Povéda, Audrey Galametz, Ryma Boumazouza, Marion-Cécile Martin, Julien Baris, Derk Daverschot, Eugene O'Higgins
Native Robustness Surrogate Model Neural Network Verification Efficient Verification Surrogate Neural Network

January 9, 2024

Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning
Jiaan Wang, Jianfeng Qu, Kexin Wang, Zhixu Li, Wen Hua, Ximing Li, An Liu
Contrastive Learning Native Robustness Knowledge Graph Dialogue Context Knowledge Grounded Semantic Perturbation

January 8, 2024

January 5, 2024

A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Convolutional Neural Network Deep Neural Network Vision Transformer Native Robustness Adversarial Example Encrypted Model

January 3, 2024

FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision Transformers
Zheng Yuan, Jie Zhang, Shiguang Shan
Vision Transformer Native Robustness Adversarial Robustness Model Robustness Pre Trained Vision Transformer Layer Normalization Adversarial Fine Tuning

January 2, 2024

Boosting Transformer's Robustness and Efficacy in PPG Signal Artifact Detection with Self-Supervised Learning
Thanh-Dung Le
Contrastive Learning Native Robustness Self Supervised Learning PPG Signal Contrastive Loss Function

Native Robustness

Papers

Enhance Eye Disease Detection using Learnable Probabilistic Discrete Latents in Machine Learning Architectures

FIMBA: Evaluating the Robustness of AI in Genomics via Feature Importance Adversarial Attacks

The landscape of Collective Awareness in multi-robot systems

An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification

Trapped in texture bias? A large scale comparison of deep instance segmentation

WAVES: Benchmarking the Robustness of Image Watermarks

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

Enhancing Wind Speed and Wind Power Forecasting Using Shape-Wise Feature Engineering: A Novel Approach for Improved Accuracy and Robustness

Enhancing Robustness of LLM-Synthetic Text Detectors for Academic Writing: A Comprehensive Analysis

Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes

Surrogate Neural Networks Local Stability for Aircraft Predictive Maintenance

Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations

Robustness Assessment of a Runway Object Classifier for Safe Aircraft Taxiing

A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples

FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision Transformers

Boosting Transformer's Robustness and Efficacy in PPG Signal Artifact Detection with Self-Supervised Learning

Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code

How Smooth Is Attention?

Robustness, Efficiency, or Privacy: Pick Two in Machine Learning