ai-exploits - A collection of real world AI/ML exploits for resp

项目说明

<di="center">

AI Exploits

<img width="250" src=" alt="AI Exploits Logo">

</div>

The AI world has a security problem and it's not just in the inputs given to LLMs such as ChatGPT. Based
on research done by Protect AI and independent security experts on the Huntr Bug Bounty Platform, there are far more impactful and practical attacks
against the tools, libraries and frameworks used to build, train, and deploy machine learning models. Many of these
attacks lead to complete system takeovers and/or loss of sensitive data, models, or credentials most often without the need
for authentication.

With the release of this repository, Protect AI hopes to demystify to the Information Security community what practical attacks against AI/Machine Learning infrastructure look like in the real world and raise awareness to the amount of components that currently exist in the AI/ML ecosystem. More can be found here:
* No Report
* December Report
* January Report
* February Report
* March Report
* April Report
* May Report
* June Report
* July Report

O

This repository, ai-exploits, is a collection of exploits and scanning templates for responsibly disclosed affecting machine learning tools.

Each tool has a number of subfolders containing three types of utilities: Metasploit modules, Nuclei templates
and CSRF templates. Metasploit modules are for security professionals looking to exploit the and Nuclei templates are for scanning a large number of remote servers to determine if they're .

Demo

Video demonstrating running one of the Metasploit modules against Ray:

![Exploit Demo]()

Setup & Usage

The easiest way to use the modules and scanning templates is to build and run the Docker image provided by the Dockerfile in this repository. The Docker image will ha and Nuclei already installed along with all the necessary configuration.

Docker

1. Build the image:

2. Run the docker image:

The latter command will drop you into a bash session in the container with msfconsole and nuclei ready to go.

Using the Metasploit Modules

#### With Docker

Start the Metasploit console (the new modules will be a under the exploits/protectai category), load a module, set the options, and run the exploit.

#### With Metasploit Installed Locally

Create a folder ~/.msf4/modules/exploits/protectai and copy the exploit modules into it.

Using Nuclei Templates

Nuclei is a scanning engine which can be used to scan large numbers of servers for known in web applications and networks.

Na to nuclei templates folder such as ai-exploits/mlflow/nuclei-templates. In the Docker container these are stored in the /root/nuclei-templates folder. Then simply point to the template file and the target server.

Using CSRF Templates

Cross-Site Request Forgery (CSRF) enable attackers to stand up a web ser a malicious HTML page
that will execute a request to the target server on behalf of the . This is a common attack for exploiting
in web applications, including web applications which are only exposed on the localhost interface and
not to the broader network. Below is a simple demo example of how to use a CSRF template to exploit a in a
web application.

Start a web server in the csrf-templates folder. Python allows one to stand up a simple web server in any
directory. Na to the template folder and start the server.

Now visit the web ser you just stood up () and hit F12 to open
the de tools, then click the Network tab. Click the link to ray-cmd-injection-csrf.html. You should see that
the browser sent a request to the server on your behalf.

Contribution Guidelines

We welcome contributions to this repository. Please read our Contribution Guidelines for more information on how to contribute.

License

This project is licensed under the Apache 2.0 License.

项目信息

开发语言：Python

Star 数：1748

技术要点

该项目属于漏洞知识库方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities 展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。