This repository contains the code that implements the Distributed and Oclussion-Robust Patch (DorPatch) described in our paper "DorPatch: Distributed and Occlusion-Robust adversarial Patch to Evade…

Save or export your private and public Slack messages, threads, files, and users locally without admin privileges.

Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.

Python implementation of the ircor

A shell command to notify you via Telegram for Linux, Mac and Windows

Inference code for Llama models

Study adversarially-robust classification with rejection where rejection has cost monotonically non-increasing in the perturbation magnitude, and propose a novel defense method with strong performa…

Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)

This repository provides simple PyTorch implementations for adversarial training methods on CIFAR-10.

Pretrained models on CIFAR10/100 in PyTorch

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…

auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs

SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

SpinalNet: Deep Neural Network with Gradual Input

OpenChat: Advancing Open-source Language Models with Imperfect Data

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

A framework for adversarial attacks against token classification models

An Open-Source Package for Textual Adversarial Attack.

Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"

Must-read Papers on Textual Adversarial Attack and Defense

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

Imitation Adversarial Attacks for Black-box Neural Ranking Models

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

This repo contains the code and configuration files for reproducing object detection results of FocalNets with DINO

Pytorch implementation of RetinaNet object detection.