Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Llama Guard is a collaborative open-source safety model created by Meta AI aimed at improving the security of large language models during interactions with humans. It operates as a filtering mechanism for inputs and outputs, categorizing both prompts and replies based on potential safety risks such as toxicity, hate speech, and false information. With training on a meticulously selected dataset, Llama Guard's performance rivals or surpasses that of existing moderation frameworks, including OpenAI's Moderation API and ToxicChat. This model features an instruction-tuned framework that permits developers to tailor its classification system and output styles to cater to specific applications. As a component of Meta's extensive "Purple Llama" project, it integrates both proactive and reactive security measures to ensure the responsible use of generative AI technologies. The availability of the model weights in the public domain invites additional exploration and modifications to address the continually changing landscape of AI safety concerns, fostering innovation and collaboration in the field. This open-access approach not only enhances the community's ability to experiment but also promotes a shared commitment to ethical AI development.
Description
Plurilock AI promptGuard is a patent-pending new security tool that protects companies from data leaks when their employees are using generative AI platforms such as ChatGPT.
PromptGuard is different from other solutions that address the problem of generative AI data leakage. It doesn't block AI or individual AI prompts. PromptGuard uses a mature DLP to detect sensitive data and anonymize it prior to sending it to the AI platform. PromptGuard restores original references when the AI platform returns a response.
This preserves the workflow of AI and the query flow, allowing users to use it productively, while keeping sensitive information out of the AI platform’s hands.
PromptGuard provides a complete audit log of all queries and responses for each user. This allows companies to create an easy-to-understand record of what AI has sent and what AI has returned.
API Access
Has API
Yes
API Access
Has API
No
Integrations
ChatGPT
No
Llama
Yes
Nebius Token Factory
Yes
OpenAI
Yes
Plurilock AI Cloud
No
Plurilock AI Cloud DLP
No
Integrations
ChatGPT
Yes
Llama
No
Nebius Token Factory
No
OpenAI
No
Plurilock AI Cloud
Yes
Plurilock AI Cloud DLP
Yes
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
Yes
Live Rep (24/7)
Yes
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
No
In Person
Yes
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
Yes
Vendor Details
Company Name
Meta
Founded
2004
Country
United States
Website
ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/
Vendor Details
Company Name
Plurilock Security
Founded
2016
Country
Canada
Website
plurilock.com/products/plurilockai-promptguard/
Product Features
Product Features
Data Loss Prevention
Compliance Reporting
No
Incident Management
No
Policy Management
No
Sensitive Data Identification
No
Web Threat Management
No
Whitelisting / Blacklisting
No