Robust Classification

Follow this topic Ask about this topic

Latest papers

37 papers4 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks
Mar 18, 2026Suryasis Jana, Abhik GhoshNeural Network Robustness Robust Classification
Indian Statistical Institute, Kolkata, India
A Fractional Fox H-Function Kernel for Support Vector Machines: Robust Classification via Weighted Transmutation Operators
Mar 13, 2026Gustavo DorregoRobust Classification Kernel Methods
Departamento de Matemática, Facultad de Ciencias Exactas y Naturales y Agrimensura, Universidad Nacional del Nordeste, Corrientes, Argentina.
The Price of Robustness: Stable Classifiers Need Overparameterization
Mar 3, 2026Jonas von Berg, Adalbert Fono, Massimiliano Datres +2Overparameterization Robust Classification
Ludwig-Maximilians-Universität München Munich, Germany Munich Center for Machine Learning (MCML) · ∗now at Aleph Alpha Research · †University of Tromso, DLR-German Aerospace Center
Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits
Feb 17, 2026Gilad Nurko, Roi Benita, Yehoshua Dissen +4Robust Classification Diffusion Models
Technion – Israel Institute of Technology, Haifa, Israel · NTT, Inc., Japan.
destroR: A Benchmark and Adversarial-Training Defense for Bangla Transfer Models under Meaning-Preserving Attacks
Nov 13, 2025Saadat Rafid Ahmed, Rubayet Shareen, Radoan Sharkar +3Adversarial Text Attacks Adversarial Robustness of Language Models
Dept. of Computer Science and Engineering, BRAC University
Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spaces
Dec 29, 2024Linglingzhi Zhu, Yunqin Zhu, Yao XieDistributionally Robust Optimization Wasserstein Distributionally Robust Optimization
1H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology
Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification
Oct 28, 2024Jaedong Hwang, Brian Cheung, Zhang-Wei Hong +3Neural Network Robustness OOD Generalization
Massachusetts Institute of Technology

Mar 18, 2026J/K move · Enter open · S save

rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks

Suryasis Jana, Abhik Ghosh

Indian Statistical Institute, Kolkata, India

Neural Network Robustness Robust Classification Learning with Noisy Labels Adversarial Robustness Robust Loss Functions

Open paper AskPDF arXiv

Neural networks are central to modern artificial intelligence, yet their training remains highly sensitive to data contamination. Standard neural classifiers are trained by minimizing the categorical cross-entropy loss, corresponding to maximum likelihood estimation under a multinomial model. While statistically efficient under ideal conditions, this approach is highly vulnerable to contaminated observations including label noises corrupting supervision in the output space, and adversarial perturbations inducing worst-case deviations in the input space. In this paper, we propose a unified and statistically grounded framework for robust neural classification that addresses both forms of contamination within a single learning objective. We formulate neural network training as a minimum-divergence estimation problem and introduce rSDNet, a robust learning algorithm based on the general class of

S

-divergences. The resulting training objective inherits robustness properties from classical statistical estimation, automatically down-weighting aberrant observations through model probabilities. We establish essential population-level properties of rSDNet, including Fisher consistency, classification calibration implying Bayes optimality, and robustness guarantees under uniform label noise and infinitesimal feature contamination. Experiments on three benchmark image classification datasets show that rSDNet improves robustness to label corruption and adversarial attacks while maintaining competitive accuracy on clean data, Our results highlight minimum-divergence learning as a principled and effective framework for robust neural classification under heterogeneous data contamination.