This project organizes classic images classification neural networks based on convolution or attention, and writes training and inference python scripts

CNN image classifier implemented in Keras Notebook 🖼️.

Implementation of a CNN-based regressor for predicting autonomous vehicle steering angles using Keras

Implement Neural Network models for both a regression and a classification task using different deep learning frameworks and approaches like Pytorch and Keras Concepts.

A simple guide to a vanilla CNN for regression, potentially useful for engineering applications.

东南大学研究生课程资料整理

Python机器学习算法技术博客，有原创干货！有code实践！ 【更多内容敬请关注公众号 "算法进阶"】

Pytorch实现：使用ResNet18网络训练Cifar10数据集，测试集准确率达到95.46%(从0开始，不使用预训练模型)

Code for the paper: CNN-generated images are surprisingly easy to spot... for now https://peterwang512.github.io/CNNDetection/

Fine-tune CNN in Keras

Alzheimer's Disease Prediction by using ResNet, AlexNet

Reproduce ResNet-v2(Identity Mappings in Deep Residual Networks) with MXNet

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

a state-of-the-art-level open visual language model | 多模态预训练模型

BATT: Backoor Attack with Transformation-based Triggers

The open-sourced Python toolbox for backdoor attacks and defenses.

[ICLR2024] "Backdoor Federated Learning by Poisoning Backdoor-Critical Layers"

An official PyTorch implementation of "Unnoticeable Backdoor Attacks on Graph Neural Networks" (WWW 2023)

Input-aware Dynamic Backdoor Attack (NeurIPS 2020)

Official implementation of "Label Poisoning is All You Need".

[IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks

A comprehensive benchmark of deepfake detection

Image Super-Resolution as a Defense Against Adversarial Attacks

Official Code of "Imperceptible Adversarial Attack via Invertible Neural Networks"

A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

This repository is the official implementation of StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model