16 open-source projects similar to dreamtalecore/refool, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
The Adversarial Robustness Toolbox (ART) is an open-source library that provides a unified framework for evaluating, defending, and certifying machine learning models against adversarial threats. It wraps models from any framework behind a common estimator interface, enabling composable pipelines for attack generation, defense application, robustness certification, and privacy auditing across evasion, poisoning, and extraction threats. The library distinguishes itself by covering the full adversarial ML security lifecycle within a single toolkit. It supports gradient-based adversarial example
Train GTSRB dataset ` python main.py --dataset GTSRB --numclass 43 --a 0.3 --b 0.1 --weightdecay 0 Train CelebA dataset python main.py --dataset CelebA --numclass 8 --a 0.3 --b 0.1 --weightdecay 1e-4 `
Implementation of Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning paper
This code is the official PyTroch implementation of the Sleeper Agent. Our implementation is based on Industrial Scale Data Poisoning via Gradient Matching.
This repository contains the code to replicate experiments in our paper:
This is the official repository for AAAI'21 paper Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification. Refer to our paper in https://arxiv.org/abs/2012.11212.
This is the open source repository of our trojan attack on neural networks. The paper is published in Proc. of NDSS 2018. The slides
This repository contains code related to the paper Live Trojan Attacks On Deep Neural Networks, by Robby Costales, Chengzhi Mao, Raphael Norwitz, Bryan Kim, and Junfeng Yang. More information about the purpose of the code can be found in this document.
See requirements.txt
Environment: Python3.6.5, TensorFlow-gpu1.14 Dataset: UCF101, Model: I3D This is our paper link. You can firstly run traincleanmodel.py to get a clean-trained I3D model. The generatetrigger.py and enhancetrigger.py correspond to Backdoor Trigger Generation and Enhancing Backdoor Trigger sections…
python==3.8.3 numpy==1.19.4 tensorflow==2.4.0 opencv==4.5.1 idx2numpy==1.2.3 pytorch==1.7.0
Official repostory for Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023).
We propose a noval global backdoor trigger called Procedural Noise Trigger, which is generated by the procedural noise.
This project is developed with Python 3.6 on Ubuntu 18.04. Please run the following script to install the required packages `shell pip install -r requirements.txt `