Adversarial training is a machine learning technique that improves a model's ability to resist attacks by using deceptive inputs during training. These examples are subtly altered to provoke mistakes, ...

While numerous work has been proposed to address fairness in machine learning, existing methods do not guarantee fair predictions under imperceptible feature perturbation, and a seemingly fair model ...

This project aims to reproduce the core experiments from the NIPS paper "Do Adversarially Robust ImageNet Models Transfer Better?", exploring the impact of Adversarial Training on model ...

Abstract: Adversarial patch attacks pose a significant threat to deep learning models in real-world applications, such as autonomous driving, due to their physical feasibility and ease of deployment.

Abstract: Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is ...

Adversarial attacks on machine learning (ML) models are growing in intensity, frequency and sophistication with more enterprises admitting they have experienced an AI-related security incident. AI's ...

A digital twin is an exact virtual copy of a real-world system. Built using real-time data, they provide a platform to test, simulate, and optimize the performance of their physical counterpart. In ...