Metadata-Version: 2.1
Name: iso-adverse
Version: 0.2.0
Summary: This package is designed to simulate adversarial on pre-trained language models (pre-LLM models)
Home-page: https://github.com/iso-ai/isoadverse
Author: Jazmia Henry
Author-email: isojaz@isoai.co
License: Apache License 2.0
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# IsoAdverse Documentation

## Introduction

Welcome to **IsoAdverse**, a Python package designed to simulate adversarial on pre-trained language models (pre-LLM models). This package implements a range of attacks as described in recent research to help secure your AI Agents and LLMs.

## Installation

To install the IsoAdverse package, you can use pip:

```bash
pip install iso-adverse
```

## Quickstart

Here’s a quick example of how to use IsoAdverse to train a BERT model with adversarial training:

```python
import torch
from isoadverse.utils.data_loader import get_data_loader
from isoadverse.utils.model_loader import get_model_and_tokenizer

# Load data and model
texts = ["This is a positive sentence.", "This is a negative sentence."]
labels = torch.tensor([1, 0])
train_loader = get_data_loader(texts, labels, batch_size=2)

model, tokenizer = get_model_and_tokenizer(model_name='bert-base-uncased')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
```

## Attacks

IsoAdverse implements several adversarial attacks on text data. Below are the details of each attack.

### Fast Gradient Sign Method (FGSM)

The FGSM attack perturbs the input text by leveraging the gradients of the loss with respect to the input.

```python
from isoadverse.attacks.text_fgsm import text_fgsm_attack
print("Running FGSM Attack...")
perturbed_text = text_fgsm_attack(model, tokenizer, texts[0], torch.tensor([labels[0]]), epsilon=0.3)
print("Original Text:", texts[0])
print("Perturbed Text:", tokenizer.decode(perturbed_text[0]))
```

### Projected Gradient Descent (PGD)

The PGD attack is an iterative attack method that performs multiple steps of FGSM.

```python
from isoadverse.attacks.text_pgd import text_pgd_attack

print("\nRunning PGD Attack...")
perturbed_ids = text_fgsm_attack(model, tokenizer, texts[0], torch.tensor([labels[0]]), epsilon=0.3)
print("Original Text:", texts[0])
print("Perturbed Text:", tokenizer.decode(perturbed_ids[0]))
```

### TextBugger

TextBugger perturbs the text by introducing character-level changes.

```python
from isoadverse.attacks.textbugger import textbugger_attack

print("\nRunning TextBugger Attack...")
perturbed_text = textbugger_attack(texts[0], num_bugs=5)
print("Original Text:", texts[0])
print("Perturbed Text:", perturbed_text)
```

### DeepWordBug

DeepWordBug introduces word-level perturbations by modifying words in the text.

```python
from isoadverse.attacks.deepwordbug import deepwordbug_attack

print("\nRunning DeepWordBug Attack...")
perturbed_text = deepwordbug_attack(texts[0], num_bugs=5)
print("Original Text:", texts[0])
print("Perturbed Text:", perturbed_text)
```


## Utilities

IsoAdverse includes utility functions for loading data and models, making it easier to integrate into your existing workflow.

### Data Loader

The data loader utility helps load and prepare text datasets for training and evaluation.

```python
from isoadverse.utils.data_loader import get_data_loader

train_loader = get_data_loader(texts, labels, batch_size=2)
```

### Model Loader

The model loader utility provides pre-trained models and tokenizers.

```python
from isoadverse.utils.model_loader import get_model_and_tokenizer

model, tokenizer = get_model_and_tokenizer(model_name='bert-base-uncased')
```



