Juli-Eyre

pytorch-cnn-visualizations

Pytorch implementation of convolutional neural network visualization techniques

CNNDetection

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

DIRE

[ICCV 2023] Official implementation of the paper: "DIRE for Diffusion-Generated Image Detection"

TransferAttack

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

AIGCDetectBenchmark

CADDM

Official implementation of ID-unaware Deepfake Detection Model

Generative_Adversarial_Perturbations

Generative Adversarial Perturbations (CVPR 2018)

Audit-log-analysis

Have fun with audit log analysis :)

TransferAttackEval

Revisiting Transferable Adversarial Images (arXiv)

Intermediate-Level-Attack

[ICCV 2019] Enhancing Adversarial Example Transferability with an Intermediate Level Attack (https://arxiv.org/abs/1907.10823)

diffusion-model-deepfake-detection

[VISAPP2024] Towards the Detection of Diffusion Model Deepfakes

Adversarial_Attacks_and_Defense_NeurIPS2022

A list of papers in NeurIPS 2022 related to adversarial attack and defense / AI security.

TTP

Official repository for "On Generating Transferable Targeted Perturbations" (ICCV 2021)

ShadowAttack

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

DualAttentionAttack

Adv-Stickers_RHDE

Adversarial Stickers: A Stealthy Attack Method in the Physical World (TPAMI 2022)

Transferable_Perturbations

[NeurIPS2021] Code Release of Learning Transferable Perturbations

SemSegAdvPatch

UNICORN

TA-Bench

Code for our NeurIPS 2023 paper Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly

Towards-Transferable-Targeted-Attack

Codes for CVPR2020 paper "Towards Transferable Targeted Attack".

gdpa

feature_level_adv

Demo code for the paper: One Thing to Fool them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features

SPAA

[IEEE VR'22] SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers

PAN

Code and data for PAN and PAN-phys.

Data-efficient-UAP

TAT

Adversarial-Attacks-on-Image-Classifiers

Generating adversarial examples using Generative Adversarial Neural networks (GANs). Performed black box attacks on attacks on Madry lab challenge MNIST, CIFAR-10 models with excellent results and white box attacks on ImageNet Inception V3.

LPM

The code of LPM

gan-attack