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.

Structural Wing Model Reduction in Fluid-Structure Interactions

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

Package for adversarial attack in pytorch

Projected Gradient Descent (PGD), inverted and amplified -> prompt & generate images with CLIP

对抗测试

Defence of Five

Programa de Gestão e Desempenho (PGD) versão SESEP (Secretaria de Avaliação e Gestão da Informação) em Docker/container.

"A collection of deep learning projects from my PGD in Data Science at NED University, including CNN-based image classification and sequence processing with ConvNets, applied to datasets like Cat-Dog, Netflix, and Jena Climate."

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

Homework of Security and Privacy of Machine Learning (SPML Lectured by Shang-Tse Chen at NTU)

"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.