dats77

adversarial_examples_with_bugs

Generate (non-software) Bugs to Fool Classifiers

adv-patch-paper-list

A paper list for localized adversarial patch research

patch-defense-leaderboard

A Leaderboard for Certifiable Robustness against Adversarial Patch Attacks

Adv-Crowd-analysis

ACM Multimedia 2021, Poster

DiAP

A Data Independent Approach to Generate Adversarial Patches

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

detr

End-to-End Object Detection with Transformers

DefensivePatch

Robust-Vision-Transformer

The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)

PAR

patchadversarialattacks

AdvHash

The official implementation of our ACM MM 2021 paper "AdvHash: Set-to-set Targeted Attack on Deep Hashing with One Single Adversarial Patch".

ShadowAttack

Code of our CVPR 2022 paper "Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon"

adversarial_tshirt

Tianchi04

Adversarial attack to detectors

AdvCam-Hide-Adv-with-Natural-Styles

Code for "Adversarial Camouflage: Hiding Physical World Attacks with Natural Styles" (CVPR 2020)

fucking-algorithm

手把手撕LeetCode题目，扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.

Patch-wise-iterative-attack

3D_Adversarial_Logo

[Preprint] "Can 3D Adversarial Logos Cloak Humans?"

cocoapi

COCO API - Dataset @ http://cocodataset.org/

AdversarialMask

Original PyTorch implementation of the AdversarialMask paper

PyTorch_YOLOv2

Yolo-v2-pytorch

YOLO for object detection tasks

DualAttentionAttack

PyTorch-YOLOv3

Minimal PyTorch implementation of YOLOv3

yolov3

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

SSL4MIS

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

meta-adversarial-training

Tensorflow implementation of Meta Adversarial Training for Adversarial Patch Attacks on Tiny ImageNet.

Adversarial-Patch-3D

We use 3D modeling methods to create real-world adversarial patches (adversarial examples) for an existing scene.

Targeted_Patch-wise-plusplus_iterative_attack

The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack.