backdoor-attacks · GitHub Topics

For educational purposes only, exhaustive samples of 450+ classic/modern trojan builders including screenshots.

Malware malware-database malware-sample malware-samples rat trojan remote-control backdoor-attacks backdoors trojan-malware malware-research malware-analysis

2.7 k

4 天前

sighook / pixload

Image Payload Creating/Injecting tools

Image payloads payload-generator injection injector hacking-tool 图像处理 backdoor-attacks web-attack-payloads

Perl 1.24 k

2 年前

THUYimingLi / backdoor-learning-resources

#计算机科学#A list of backdoor learning resources

backdoor-attacks ai-security 深度学习机器学习

1.11 k

1 年前

THUYimingLi / BackdoorBox

The open-sourced Python toolbox for backdoor attacks and defenses.

backdoor-attacks

Python 555

11 天前

zux0x3a / 0xsp-Mongoose

a unique framework for cybersecurity simulation and red teaming operations, windows auditing for newer vulnerabilities, misconfigurations and privilege escalations attacks, replicate the tactics and t...

privilege-escalation toolkit 安全 Windows 0xsp-mongoose webapi agent Mongoose redteaming redteam lateral-movement impersonation backdoor-attacks

Pascal 537

3 年前

Tsuyoken / ImgBackdoor

Hide your payload into .jpg file

backdoor backdoor-attacks backdoors metasploit Exploit payload jpg

Shell 394

3 年前

ebagdasa / backdoors101

#计算机科学#Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

backdoors 机器学习 research 安全 PyTorch adversarial-machine-learning backdoor-attacks federated-learning

Python 363

2 年前

ain-soph / trojanzoo

#计算机科学#TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

PyTorch backdoor-attacks image-classification adversarial-attacks 深度学习

Python 290

10 个月前

bolunwang / backdoor

#计算机科学#Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and Privacy 2019.

Python Keras 深度学习 backdoor-attacks trojan 安全

Python 288

5 年前

penghui-yang / awesome-data-poisoning-and-backdoor-attacks

#Awesome#A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)

Awesome Lists backdoor-attacks 机器学习

259

5 个月前

zihao-ai / Awesome-Backdoor-in-Deep-Learning

#计算机科学#A curated list of papers & resources on backdoor attacks and defenses in deep learning.

Awesome Lists backdoor backdoor-attacks 深度学习 Bukkit

Python 205

1 年前

thunlp / OpenBackdoor

#自然语言处理#An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

自然语言处理 backdoor-attacks

Python 183

2 年前

sshh12 / llm_backdoor

Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without running a...

backdoor-attacks llm-security qwen2-5

Python 171

2 个月前

VinAIResearch / Warping-based_Backdoor_Attack-release

#计算机科学#WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)

backdoor-attacks 安全深度学习机器学习机器视觉

Python 124

7 个月前

bboylyg / NAD

This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://openreview.net/pdf?id=9l0K4OM-oXE) in PyTorch.

backdoor-attacks 深度神经网络 PyTorch

Python 122

3 年前

ELMERIKH / Keres

Persistent Powershell backdoor tool {😈}

backdoor-attacks Exploit payload-generator PowerShell red-team-tools reverse-shell bypass-antivirus

Python 119

1 年前

reds-lab / Narcissus

The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack...

adversarial-attacks adversarial-machine-learning ai-security backdoor-attacks

Python 115

2 年前

HalilDeniz / BackDoorSim

BackdoorSim: An Educational into Remote Administration Tools

backdoor backdoor-attacks backdoors ransomware remote-administrative-tool

Python 103

1 年前

AiGptCode / ANYDESK-BACKDOOR

You should never use malware to infiltrate a target system. With the skill of writing and exploiting technical codes, you can do the best ways of penetration. This is done in order to test and increas...

anydesk backdoor backdoor-attacks hack Hacktoberfest PowerShell Python ransomware fud fud-backdoor fud-rat kali-linux Web Windows

Python 75

1 个月前

jhcknzzm / Federated-Learning-Backdoor

ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341

backdoor-attacks federated-learning

Python 73

2 年前