ECE C147: Neural Networks & Deep Learning. Repository for "Developing Robust Networks to Defend Against Adversarial Examples". Implementing adversarial data augmentation on CNNs and RNNs.

A comprehensive GUI application for visualizing and understanding adversarial attacks on deep neural networks.

Adversarial example generation (FGSM/gradient sign) and adversarial training for robustness in TensorFlow 2; clean vs adversarial evaluation.

Label Smoothing and Adversarial Robustness

Adversarial Attack using a DCGAN

Implementation of FGSM (Fast Gradient Sign Method) attack on fine-tuned MobileNet architecture trained for flood detection in images.

Fast Gradient Sign Method Adversarial Attack on Digit Recognition Model

This repository contains the implementation of two adversarial example attack methods FGSM, IFGSM and one Input Transformation defense mechanism against all attacks using Imagenet dataset.

adversarial patch train by I-FGSM to attack on MTCNN face detection system

Implementation and evaluation for Deep Learning Project 3 (Spring 2025, NYU Tandon). We attack a pretrained ResNet-34 model using ℓ∞-bounded adversarial perturbations, including FGSM, PGD, Momentum PGD, and Patch PGD, and assess transferability to DenseNet-121.

This repository contains the solution for Assignment 1 of the Deep Learning course at the University of Tehran, focusing on image classification, adversarial attacks, and defensive techniques..

FGSM attack Pytorch module for semantic segmentation networks, with examples provided for Deeplab V3.

Machine Learning (2019 Spring)

Convolutional Neural Networks

Simple examples done in MxNet

Adversarial attacks to SRNet

FGSM(Fast Gradient Sign Method)

using adversarial attacks to confuse deep-chicken-terminator 🛡️ 🐔

Experimental Adversarial Attack notebooks on CV models