Agentic Security – Enhancing LLM Resilience With Open-Source Vulnerability Scanning

In an era where large language models (LLMs) are integral to technological advancements, ensuring their security is paramount.

Agentic Security offers a pioneering open-source vulnerability scanner designed to robustly test and enhance the resilience of LLMs.

This tool not only integrates seamlessly but also provides customizable attack simulations to safeguard against emerging threats.

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

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: 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

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

....

For more information click here.