projected-gradient-descent

CAP6938-Fall2025: This is a PyTorch framework for benchmarking ResNet18 and ViT robustness under PGD and targeted Controlled PGD (CPGD) adversarial attacks across six image datasets. UCF Trustworthy ML.

PyTorch implementation of projected gradient descent (PGD) adversarial noise attack

A Python toolkit for large-scale constrained and unconstrained numerical optimization.

Hands-on AI security workshop by GDSC Asia Pacific University – explore the fundamentals of attacking machine learning systems through white-box and black-box techniques. Learn to evade image classifiers and manipulate LLM behavior using real-world tools and methods.

Interactive gradient descent visualizer for optimization algorithms. Explore GD, SGD, projected gradient descent, and Frank-Wolfe methods step-by-step.

Project developed during the course of 'Optimization for Data Science' in the University of Padua. The project provides an Implementation of Frank-Wolfe Methods for Recommender Systems in Python.