Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/meta-llama/PurpleLlama

Set of tools to assess and improve LLM security.
https://github.com/meta-llama/PurpleLlama

Last synced: 9 days ago
JSON representation

Set of tools to assess and improve LLM security.

Awesome Lists containing this project

README 

        


  






        🤗  Models on Hugging Face&nbsp |  Blog&nbsp |  Website&nbsp | CyberSec Eval Paper&nbsp&nbsp | Llama Guard Paper&nbsp





---



# Purple Llama



Purple Llama is an umbrella project that over time will bring together tools

and evals to help the community build responsibly with open generative AI

models. The initial release will include tools and evals for Cyber Security and

Input/Output safeguards but we plan to contribute more in the near future.



## Why purple?



Borrowing a [concept](https://www.youtube.com/watch?v=ab_Fdp6FVDI) from the

cybersecurity world, we believe that to truly mitigate the challenges which

generative AI presents, we need to take both attack (red team) and defensive

(blue team) postures. Purple teaming, composed of both red and blue team

responsibilities, is a collaborative approach to evaluating and mitigating

potential risks and the same ethos applies to generative AI and hence our

investment in Purple Llama will be comprehensive.



## License



Components within the Purple Llama project will be licensed permissively enabling both research and commercial usage.

We believe this is a major step towards enabling community collaboration and standardizing the development and usage of trust and safety tools for generative AI development.

More concretely evals and benchmarks are licensed under the MIT license while any models use the corresponding Llama Community license. See the table below:



| **Component Type** |            **Components**            |                                          **License**                                           |

| :----------------- | :----------------------------------: | :--------------------------------------------------------------------------------------------: |

| Evals/Benchmarks   | Cyber Security Eval (others to come) |                                              MIT                                               |

| Safeguard             |             Llama Guard              | [Llama 2 Community License](https://github.com/facebookresearch/PurpleLlama/blob/main/LICENSE) |

| Safeguard             |             Llama Guard 2            | [Llama 3 Community License](https://github.com/meta-llama/llama3/blob/main/LICENSE) |

| Safeguard             |             Llama Guard 3-8B            | [Llama 3.2 Community License](LICENSE) |

| Safeguard             |             Llama Guard 3-1B            | [Llama 3.2 Community License](LICENSE) |

| Safeguard             |             Llama Guard 3-11B-vision            | [Llama 3.2 Community License](LICENSE) |

| Safeguard             |             Prompt Guard            | [Llama 3.2 Community License](LICENSE) |

| Safeguard          |             Code Shield              | MIT |



## System-Level Safeguards



As we outlined in Llama 3’s

[Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/), we

recommend that all inputs and outputs to the LLM be checked and filtered in

accordance with content guidelines appropriate to the application.



### Llama Guard



Llama Guard 3 consists of a series of high-performance input and output moderation models designed to support developers to detect various common types of violating content.



They were built by fine-tuning Meta-Llama 3.1 and 3.2 models and optimized to support the detection of the MLCommons standard hazards taxonomy, catering to a range of developer use cases.

They support the release of Llama 3.2 capabilities, including 7 new languages, a 128k context window, and image reasoning. Llama Guard 3 models were also optimized to detect helpful cyberattack responses and prevent malicious code output by LLMs to be executed in hosting environments for Llama systems using code interpreters.



### Prompt Guard

Prompt Guard is a powerful tool for protecting LLM powered applications from malicious prompts to ensure their security and integrity.



Categories of prompt attacks include prompt injection and jailbreaking:



* Prompt Injections are inputs that exploit the inclusion of untrusted data from third parties into the context window of a model to get it to execute unintended instructions.

* Jailbreaks are malicious instructions designed to override the safety and security features built into a model.



### Code Shield



Code Shield adds support for inference-time filtering of insecure code produced by LLMs. Code Shield offers mitigation of insecure code suggestions risk, code interpreter abuse prevention, and secure command execution. [CodeShield Example Notebook](https://github.com/meta-llama/PurpleLlama/blob/main/CodeShield/notebook/CodeShieldUsageDemo.ipynb).



## Evals & Benchmarks



### Cybersecurity



#### CyberSec Eval v1

CyberSec Eval v1 was what we believe was the first industry-wide set of cybersecurity safety evaluations for LLMs. These benchmarks are based on industry guidance and standards (e.g., CWE and MITRE ATT&CK) and built in collaboration with our security subject matter experts. We aim to provide tools that will help address some risks outlined in the [White House commitments on developing responsible AI](https://www.whitehouse.gov/briefing-room/statements-releases/2023/07/21/fact-sheet-biden-harris-administration-secures-voluntary-commitments-from-leading-artificial-intelligence-companies-to-manage-the-risks-posed-by-ai/), including:

* Metrics for quantifying LLM cybersecurity risks.

* Tools to evaluate the frequency of insecure code suggestions.

* Tools to evaluate LLMs to make it harder to generate malicious code or aid in carrying out cyberattacks.



We believe these tools will reduce the frequency of LLMs suggesting insecure AI-generated code and reduce their helpfulness to cyber adversaries. Our initial results show that there are meaningful cybersecurity risks for LLMs, both with recommending insecure code and for complying with malicious requests. See our [Cybersec Eval paper](https://ai.meta.com/research/publications/purple-llama-cyberseceval-a-benchmark-for-evaluating-the-cybersecurity-risks-of-large-language-models/) for more details.



#### CyberSec Eval 2

CyberSec Eval 2 expands on its predecessor by measuring an LLM’s propensity to abuse a code interpreter, offensive cybersecurity capabilities, and susceptibility to prompt injection. You can read the paper [here](https://ai.meta.com/research/publications/cyberseceval-2-a-wide-ranging-cybersecurity-evaluation-suite-for-large-language-models/).



You can also check out the 🤗 leaderboard [here](https://huggingface.co/spaces/facebook/CyberSecEval).



#### CyberSec Eval 3

The newly released CyberSec Eval 3 features three additional test suites: visual prompt injection tests, spear phishing capability tests, and autonomous offensive cyber operations tests.



## Getting Started



As part of the [Llama reference system](https://github.com/meta-llama/llama-agentic-system), we’re integrating a safety layer to facilitate adoption and deployment of these safeguards.

Resources to get started with the safeguards are available in the [Llama-recipe GitHub repository](https://github.com/meta-llama/llama-recipes).



## FAQ



For a running list of frequently asked questions, for not only Purple Llama

components but also generally for Llama models, see the FAQ

[here](https://ai.meta.com/llama/faq/).



## Join the Purple Llama community



See the [CONTRIBUTING](CONTRIBUTING.md) file for how to help out.