Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Metasploit for machine learning.
| Date | Stars |
|---|---|
| 2026-07-31 | 570 |
| 2026-08-06 | 571 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<img src="https://github.com/cchio/deep-pwning/blob/master/dpwn/repo-assets/dpwn-splash.png?raw=true" alt="Deep-pwning splash"/>
</p>
Deep-pwning is a lightweight framework for experimenting with machine learning models with the goal of evaluating their robustness against a motivated adversary.
Note that deep-pwning in its current state is ***no where*** close to maturity or completion. It is meant to be experimented with, expanded upon, and extended by you. Only then can we help it truly become the goto __penetration testing toolkit for statistical machine learning models__.
## Background
Researchers have found that it is surprisingly trivial to trick a machine learning model (classifier, clusterer, regressor etc.) into making an objectively wrong decisions. This field of research is called [Adversarial Machine Learning](https://people.eecs.berkeley.edu/~tygar/papers/SML2/Adversarial_AISEC.pdf). It is not hyperbole to claim that any motivated attacker can bypass any machine learning system, given enough information and time. However, this issue is often overlooked when architects and engineers design and build machine learning systems. The consequences are worrying when these systems are put into use in critical scenarios, such as in the medical, transportation, financial, or security-related fields.
Hence, when one is evaluating the efficacy of applications using machine learning, their malleability in an adversarial setting should be measured alongside the system's precision and recall.
This tool was released at DEF CON 24 in Las Vegas, August 2016, during a talk titled [Machine Duping 101: Pwning Deep Learning Systems](https://www.defcon.org/html/defcon-24/dc-24-speakers.html#Chio).
## Structure
This framework is built on top of [Tensorflow](https://www.tensorflow.org/), and many of the included examples in this repository are modified Tensorflow examples obtained from the [Tensorflow GitHub repository](https://github.com/tensorflow/tensorflow).
All of the included examples and code implement **deep neural networks**, but they can be used to generate adversarial images for similarly tasked classifiers that are not implemented with deep neural networks. This is because of the phenomenon of 'transferability' in machine learning, which was Papernot et al. expounded expertly upon in [this paper](https://arxiv.org/abs/1605.07277). This means means that adversarial samples crafted with a DNN model *A* may be able to fool another distinctly structured DNN model *B*, as well as some other SVM model *C*.
This figure taken from the aforementioned paper (Papernot et al.) shows the percentage of successful adversarial misclassification for a source model (used to generate the adversarial sample) on a target model (upon which the adversarial sample is tested).
<p align="center">
<img src="https://github.com/cchio/deep-pwning/blob/master/dpwn/repo-assets/transferability-misclassificaiton-matrix.png?raw=true" alt="Transferability Misclassificaiton Matrixh"/>
</p>
## Components
Deep-pwning is modularized into several components to minimize code repetition. Because of the vastly different nature of potential classification tasks, the current iteration of the code is optimized for classifying **images** and **phrases** (using word vectors).
These are the code modules that make up the current iteration of Deep-pwning:
1. Drivers
The **drivers** are the *main* execution point of the code. This is where you can tie the different modules and components together, and where you can inject more customizations into the adversarial generation processes.
2. Models
This is where the actual machine learning model implementations are located. For example, the provided ```lenet5``` model definition is located in the ```model()``` function witihn ```lenet5.py```. It defines the network as the following:
```
-> Input
-> Convolutional Layer 1
-> Max Pooling Layer 1
-> Convolutional LayerExcerpt of 11,088 characters
Read on GitHub
14
1
Joshua Herman · A Cons Apart · Israel
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:642da27d428a2e83, llm:description: 'Metasploit for machine learning' (repository description)
matched fp:642da27d428a2e83, llm:description: 'Metasploit for machine learning' (repository description)
matched fp:642da27d428a2e83, llm:description: 'Metasploit for machine learning' (repository description)