Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

A lightweight Python package for setting up robustness experiments and to compute robustness distributions.

NAACL 2022 paper on Analyzing Modality Robustness in Multimodal Sentiment Analysis

We investigated corruption robustness across different architectures including Convolutional Neural Networks, Vision Transformers, and the MLP-Mixer.

Official Code for "Can These Views Be One Scene?"

IQClab - gateway for robustness analysis and control design

Official repository of our submission "Adversarial Robustness through the Lens of Convolutional Filters" for the CVPR2022 Workshop "The Art of Robustness: Devil and Angel in Adversarial Machine Learning Workshop"

Potential of 2D Priors for Improving Robustness of Ill-Posed 3D Reconstruction

[Elsevier Image and Vision Computing] How robust are discriminatively trained zero-shot learning models?

Analyzing and Improving the Robustness of Tabular Classifiers using Counterfactual Explanations

Official repository for the paper: "On Adversarial Training without Perturbing all Examples", Accepted at ICLR 2024

To verify and analyze classification properties of the neural networks when a small perturbation is applied to the image from MNIST, CIFAR-10 (and both with prepared Blured-Image) dataset.

Research project that focuses on observing the Resilience of Delhi Road Networks to Traffic Disruptions

Uncertainty Quantification and Sensitivity Analysis developed by the PPMI Group at UKAEA

Project repo for UWaterloo graduate course - ECE653. It involves comparing robustness, implementing new GAN based attack and extending CleverHans library with DeepFool attack.

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis

𝒮𝒟-2 · System Deviation Diagnosis — a robustness diagnosis framework for end-to-end (E2E) autonomous driving. Decomposes the driving pipeline (vision → semantic → planning → control → outcome), measures stage-wise deviation between clean and stress CARLA runs, and localizes where robustness first collapses (InterFuser, TransFuser).

demonstration of methods implemented in my thesis "Robustness assessment of the biological processor using hyperellipsoids"

Comparative analysis of monocular depth estimation methods (ResNet-50, frozen Stable Diffusion UNet, I-JEPA, SD+I-JEPA fusion, DepthAnything V2) with robustness evaluation under fog, blur, and low-light on NYU Depth V2.

Network Analysis of Robustness