Robust Classifier

Robust classifiers aim to build machine learning models that are resilient to various forms of noise, uncertainty, and adversarial attacks, maintaining high accuracy even under challenging conditions. Current research focuses on improving robustness through techniques like adversarial training, meta-learning to mitigate spurious correlations, and employing architectures such as diffusion models and randomized smoothing. These advancements are crucial for deploying reliable machine learning systems in real-world applications where data quality and distribution shifts are common, impacting fields ranging from image recognition to safety-critical systems.

Papers

May 23, 2023

In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models
Afra Amini, Massimiliano Ciaramita
Large Language Model Context Learning Classification Task Robust Classifier

April 28, 2023

On the existence of solutions to adversarial training in multiclass classification
Nicolas Garcia Trillos, Matt Jacobs, Jakwang Kim
Adversarial Training Adversarial Perturbation Solution Path Multiclass Classification Robust Classifier Learning Problem Agnostic Adversarial

April 25, 2023

Certifying Ensembles: A General Certification Theory with S-Lipschitzness
Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi
Native Robustness Robust Classifier Multiple Classifier Lipschitz Learning

April 18, 2023

A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift
Firas Bayram, Bestoun S. Ahmed
Machine Learning Model Random Forest Covariate Shift Robust Classifier Machine Learning Robustness Distribution Change

March 4, 2023

RoLNiP: Robust Learning Using Noisy Pairwise Comparisons
Samartha S Maheshwara, Naresh Manwani
Loss Function Robust Learning Pairwise Comparison Robust Classifier Class Conditional Robust Method

February 26, 2023

Autoencoders as Pattern Filters
M. Andrecut
Supervised Autoencoder Complex Pattern Robust Classifier Online Filtering Pattern Filter

February 2, 2023

On the Robustness of Randomized Ensembles to Adversarial Perturbations
Hassan Dbouk, Naresh R. Shanbhag
Native Robustness Adversarial Perturbation Robust Classifier Ensemble Classifier Fast Minimum Norm Attack

February 1, 2023

Simplicity Bias in 1-Hidden Layer Neural Networks
Depen Morwani, Jatin Batra, Prateek Jain, Praneeth Netrapalli
Neural Network Ensemble Approach Robust Classifier Simplicity Bias

January 29, 2023

Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
Yatong Bai, Brendon G. Anderson, Aerin Kim, Somayeh Sojoudi
Native Robustness Adversarial Robustness Simple Classifier Robust Classifier Accuracy Robustness Adversarial Region Adaptive Smoothing

December 6, 2022

Domain Generalization Strategy to Train Classifiers Robust to Spatial-Temporal Shift
Minseok Seo, Doyi Kim, Seungheon Shin, Eunbin Kim, Sewoong Ahn, Yeji Choi
Domain Generalization Temporal Shift Robust Classifier Weather Prediction Model Temporal Robustness Weather Prediction Task

September 23, 2022

MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier
Mozhdeh Rouhsedaghat, Masoud Monajatipoor, C. -C. Jay Kuo, Iacopo Masi
LangId Magic Spell Robust Classifier Binary Mask Guided Image Synthesis Machine Perception Synthetic Gradient

August 18, 2022

Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
Bahjat Kawar, Roy Ganz, Michael Elad
Generative Model Image Synthesis Generative Diffusion Model Denoising Diffusion Robust Classifier Gradient Based Adversarial Classifier Guidance

July 18, 2022

Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan
Distribution Shift Diverse Ensemble Robust Model Robust Classifier Accuracy Trade Distribution Accuracy Distribution Calibration

June 1, 2022

On the Perils of Cascading Robust Classifiers
Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina Pasareanu, Matt Fredrikson
Adversarial Attack Black Box Model Robust Classifier Robust Neural Network Certifiable Robustness

March 13, 2022

Context-LSTM: a robust classifier for video detection on UCF101
Dengshan Li, Rujing Wang
Human Action Recognition LSTM Model Robust Classifier Video Detection Video Action Detection Context Neural Network

February 5, 2022

Adversarial Detector with Robust Classifier
Takayuki Osakabe, Maungmaung Aprilpyone, Sayaka Shiota, Hitoshi Kiya
Adversarial Example Adversarial Detection Robust Classifier