Models and examples built with TensorFlow

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Refine high-quality datasets and visual AI models

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

How to train a TensorFlow Object Detection Classifier for multiple object detection on Windows

POT : Python Optimal Transport

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"

SincNet is a neural architecture for efficiently processing raw audio samples.

(Open Source) Computer Vision + Deep Learning + League of Legends

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

Implementation of Single Shot MultiBox Detector in TensorFlow, to detect and classify traffic signs

Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

Model extraction attacks on Machine-Learning-as-a-Service platforms.

ImageNet-R(endition) and DeepAugment (ICCV 2021)

Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (published in ICLR2018)

DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)

Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873

Realization of paper: "Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN" 2017

MagNet: a Two-Pronged Defense against Adversarial Examples

Tensorflow implementation of "Towards the Automatic Anime Characters Creation with Generative Adversarial Networks"

[TACL] Code for "Red Teaming Language Model Detectors with Language Models"

Code implementation of the paper "With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning", at USENIX Security 2018

ICML Workshop 18 - Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model

ACCV'18 workshop - Synthesizing New Retinal Symptom Images by Multiple Generative Models

Simple electronic devices measurement GUI

repository for a paper, Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

Pretrained TorchVision models on CIFAR10 dataset (with weights)

tmp

An implementation of vggish in keras with tf backend