Skip to content

Latest commit

 

History

History
305 lines (230 loc) · 9.46 KB

Readme.md

File metadata and controls

305 lines (230 loc) · 9.46 KB

Agentic Security

The open-source Agentic LLM Vulnerability Scanner

GitHub Contributors GitHub Last Commit Downloads GitHub Issues GitHub Pull Requests Github License

Features

  • Customizable Rule Sets or Agent based attacks🛠️
  • Comprehensive fuzzing for any LLMs 🧪
  • LLM API integration and stress testing 🛠️
  • Wide range of fuzzing and attack techniques 🌀

Note: Please be aware that Agentic Security is designed as a safety scanner tool and not a foolproof solution. It cannot guarantee complete protection against all possible threats.

📦 Installation

To get started with Agentic Security, simply install the package using pip:

pip install agentic_security

⛓️ Quick Start

agentic_security

2024-04-13 13:21:31.157 | INFO     | agentic_security.probe_data.data:load_local_csv:273 - Found 1 CSV files
2024-04-13 13:21:31.157 | INFO     | agentic_security.probe_data.data:load_local_csv:274 - CSV files: ['prompts.csv']
INFO:     Started server process [18524]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8718 (Press CTRL+C to quit)
python -m agentic_security
# or
agentic_security --help


agentic_security --port=PORT --host=HOST

UI 🧙

booking-screen

LLM kwargs

Agentic Security uses plain text HTTP spec like:

POST https://api.openai.com/v1/chat/completions
Authorization: Bearer sk-xxxxxxxxx
Content-Type: application/json

{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "<<PROMPT>>"}],
     "temperature": 0.7
}

Where <<PROMPT>> will be replaced with the actual attack vector during the scan, insert the Bearer XXXXX header value with your app credentials.

Adding LLM integration templates

TBD

....

Adding own dataset

To add your own dataset you can place one or multiples csv files with prompt column, this data will be loaded on agentic_security startup

2024-04-13 13:21:31.157 | INFO     | agentic_security.probe_data.data:load_local_csv:273 - Found 1 CSV files
2024-04-13 13:21:31.157 | INFO     | agentic_security.probe_data.data:load_local_csv:274 - CSV files: ['prompts.csv']

Run as CI check

ci.py

from agentic_security import AgenticSecurity

spec = """
POST http://0.0.0.0:8718/v1/self-probe
Authorization: Bearer XXXXX
Content-Type: application/json

{
    "prompt": "<<PROMPT>>"
}
"""
result = AgenticSecurity.scan(llmSpec=spec)

# module: failure rate
# {"Local CSV": 79.65116279069767, "llm-adaptive-attacks": 20.0}
exit(max(r.values()) > 20)
python ci.py
2024-04-27 17:15:13.545 | INFO     | agentic_security.probe_data.data:load_local_csv:279 - Found 1 CSV files
2024-04-27 17:15:13.545 | INFO     | agentic_security.probe_data.data:load_local_csv:280 - CSV files: ['prompts.csv']
0it [00:00, ?it/s][INFO] 2024-04-27 17:15:13.74 | data:prepare_prompts:195 | Loading Custom CSV
[INFO] 2024-04-27 17:15:13.74 | fuzzer:perform_scan:53 | Scanning Local CSV 15
18it [00:00, 176.88it/s]
+-----------+--------------+--------+
|  Module   | Failure Rate | Status |
+-----------+--------------+--------+
| Local CSV |    80.0%     |   ✘    |
+-----------+--------------+--------+

Extending dataset collections

  1. Add new metadata to agentic_security.probe_data.REGISTRY
    {
        "dataset_name": "markush1/LLM-Jailbreak-Classifier",
        "num_prompts": 1119,
        "tokens": 19758,
        "approx_cost": 0.0,
        "source": "Hugging Face Datasets",
        "selected": True,
        "dynamic": False,
        "url": "https://huggingface.co/markush1/LLM-Jailbreak-Classifier",
    },

and implement loader into

@dataclass
class ProbeDataset:
    dataset_name: str
    metadata: dict
    prompts: list[str]
    tokens: int
    approx_cost: float

    def metadata_summary(self):
        return {
            "dataset_name": self.dataset_name,
            "num_prompts": len(self.prompts),
            "tokens": self.tokens,
            "approx_cost": self.approx_cost,
        }

Dynamic datasets with mutations

One of the current examples uses sampling for the existing preloaded prompt data and applying mutations yielding a new dataset

class Stenography:
    fn_library = {
        "rot5": stenography_fn.rot5,
        "rot13": stenography_fn.rot13,
        "base64": stenography_fn.base64_encode,
        "mirror": stenography_fn.mirror_words,
        "random_case": stenography_fn.randomize_letter_case,
        "scramble_words": stenography_fn.scramble_words,
        "noise_characters": stenography_fn.insert_noise_characters,
        "substitute_with_ascii": stenography_fn.substitute_with_ascii,
        "remove_vowels": stenography_fn.remove_vowels,
        "zigzag_obfuscation": stenography_fn.zigzag_obfuscation,
    }

    def __init__(self, prompt_groups: [ProbeDataset]):
        self.prompt_groups = prompt_groups

    def apply(self):
        for prompt_group in self.prompt_groups:

            size = len(prompt_group.prompts)
            for name, fn in self.fn_library.items():
                logger.info(f"Applying {name} to {prompt_group.dataset_name}")
                selected_prompts = random.sample(prompt_group.prompts, int(size * 0.25))
                prompts = [
                    f"Follow the instructions in {name}: {fn(p)}"
                    for p in selected_prompts
                ]
                yield ProbeDataset(
                    dataset_name=f"stenography.{name}({prompt_group.dataset_name})",
                    metadata={},
                    prompts=prompts,
                    tokens=count_words_in_list(prompts),
                    approx_cost=0.0,
                )

Probe endpoint

In the example of custom integration, we use /v1/self-probe for the sake of integration testing.

POST https://agentic_security-preview.vercel.app/v1/self-probe
Authorization: Bearer XXXXX
Content-Type: application/json

{
    "prompt": "<<PROMPT>>"
}

This endpoint randomly mimics the refusal of a fake LLM.

@app.post("/v1/self-probe")
def self_probe(probe: Probe):
    refuse = random.random() < 0.2
    message = random.choice(REFUSAL_MARKS) if refuse else "This is a test!"
    message = probe.prompt + " " + message
    return {
        "id": "chatcmpl-abc123",
        "object": "chat.completion",
        "created": 1677858242,
        "model": "gpt-3.5-turbo-0613",
        "usage": {"prompt_tokens": 13, "completion_tokens": 7, "total_tokens": 20},
        "choices": [
            {
                "message": {"role": "assistant", "content": message},
                "logprobs": None,
                "finish_reason": "stop",
                "index": 0,
            }
        ],
    }

CI/CD integration

TBD

Documentation

For more detailed information on how to use Agentic Security, including advanced features and customization options, please refer to the official documentation.

Roadmap and Future Goals

  • Expand dataset variety
  • Introduce two new attack vectors
  • Develop initial attacker LLM
  • Complete integration of OWASP Top 10 classification
Tool Source Integrated
Garak leondz/garak
InspectAI UKGovernmentBEIS/inspect_ai
llm-adaptive-attacks tml-epfl/llm-adaptive-attacks
Custom Huggingface Datasets markush1/LLM-Jailbreak-Classifier
Local CSV Datasets -

Note: All dates are tentative and subject to change based on project progress and priorities.

👋 Contributing

Contributions to Agentic Security are welcome! If you'd like to contribute, please follow these steps:

  • Fork the repository on GitHub
  • Create a new branch for your changes
  • Commit your changes to the new branch
  • Push your changes to the forked repository
  • Open a pull request to the main Agentic Security repository

Before contributing, please read the contributing guidelines.

License

Agentic Security is released under the Apache License v2.

Contact us

Repo Activity