Pytorch-Named-Entity-Recognition-with-transformers
Implementation of gradient-based adversarial attack(FGSM,MI-FGSM,PGD)
A Parallel Graphlet Decomposition Library for Large Graphs
Implementation of adversarial training under fast-gradient sign method (FGSM), projected gradient descent (PGD) and CW using Wide-ResNet-28-10 on cifar-10. Sample code is re-usable despite changing the model or dataset.
Reproduce multiple adversarial attack methods
Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.
Official implementation of the paper: "REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions", IEEE WACV, 2022
some adversarial attacks implemented on different ml models to see their effect.
Code implementation of our AAAI'22 paper "Improved Gradient-Based Adversarial Attacks for Quantized Networks"
some tricks for sentence representation
Protect artwork from AI scraping with adversarial perturbations, imperceptible to humans, but poison to vision models. Upload an image and an ensemble PGD attack (ResNet-50 + MobileNetV2) fools classifiers server-side, with accounts, a gallery, and likes. Built for the IBM AI Builders Challenge.
Adversarial robustness evaluation framework for ML-based NIDS. Categorical robustness framework, the False Champion Problem. Backs IEEE Access submission. DoD-funded research with West Point.
Projected Gradient Descent (PGD), inverted and amplified -> prompt & generate images with CLIP
A cross-layer IoMT anomaly detection dataset with real traffic, labeled attacks, and FGSM/PGD adversarial samples for robust security research.
Programa de Gestão e Desempenho (PGD) versão SESEP (Secretaria de Avaliação e Gestão da Informação) em Docker/container.
"Security Evaluation of a Face Recognition System": Final project for the AI for Cybersecurity course. This repository explores the robustness of deep learning image classifiers against adversarial attacks and evaluating common defense strategies.
A PyTorch implementation exploring adversarial attacks (FGSM & PGD) and adversarial training for robust image classification on the CIFAR-10 dataset.
Add a description, image, and links to the pgd topic page so that developers can more easily learn about it.
To associate your repository with the pgd topic, visit your repo's landing page and select "manage topics."