Deployed on AWS
This solution predicts and prevents jailbreak attempts, ensuring your prompts remain safe from injection attacks.
Overview
The LLM Shield is a cutting-edge security solution designed to protect your language model from malicious prompts and attacks. Acting as a robust LLM firewall, it utilizes sophisticated algorithms to predict whether a prompt is a jailbreak attempt, safe, or an injection attack. This proactive approach ensures your LLM-based systems operate securely and reliably, minimizing the risk of unauthorized access or manipulation.
It utilizes state-of-the-art technology to accurately predict and categorize prompts. It offers instant protection against injection attacks and jailbreak attempts, safeguarding your LLM in real time. It is easy to integrate with existing systems, providing seamless protection without complicating your workflow.
Highlights
- Protects your LLMs from malicious prompts, ensuring safe and reliable operation.
- Automates threat detection, saving time and resources while maintaining high security standards.
Details
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $100.00 |
ml.t2.medium Inference (Real-Time) Recommended | Model inference on the ml.t2.medium instance type, real-time mode | $5.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $100.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $100.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $100.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $100.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $100.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $100.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $100.00 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $100.00 |
Vendor refund policy
We do not provide any usage related refunds at this time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Feature updates and bug fixes
Additional details
Inputs
- Summary
A json document conatining the text to be analyzed in the format { "Prompt": "Some Text" }
- Limitations for input type
- Test should be utf-8 encoded
- Input MIME type
- application/json
https://github.com/HDTS-user/llm-shield/tree/main/input
https://github.com/HDTS-user/llm-shield/tree/main/input
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
Prompt | Prompt being passed on to the LLM | Type: FreeText
Limitations: Less than 1024 tokens | Yes |
Resources
Support
Vendor support
Business hours email support marketplaceSupp@harman.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
The Intelligent Healthcare Platform empowers associates with adaptive, agentic AI-powered resolution assistance, transforming healthcare associate and customer service representative interactions. By leveraging advanced LLMs (large language models), the platform ingests and analyzes member/patient/customer inquiries in real-time, extracting relevant data and documents, and coaching associates with dynamic in-call tips and automated responses. The platform delivers voice-to-text conversation transcripts, personalized outreach in preferred languages, and post-call summarization providing faster, more accurate, and confident support.
Unleash the Power of NA-Gen-AI
Elevate your data journey with us, where security, metadata illumination, precision in domain-driven lake architecture, and the power of prompt engineering converge to redefine data analytics and Gen AI excellence.
llmware is a unified, open source, extensible framework for LLM-based application patterns including Retrieval Augmented Generation (RAG).
Use for chat, RAG, medical summarization, open-book question answering with context of up to 32K tokens.
OpenAI Proxy Server (LLM Gateway) to call 100+ LLM APIs using the OpenAI format Bedrock, Huggingface, VertexAI, TogetherAI, Azure OpenAI, OpenAI, etc. Get started with Opensource LiteLLM here: https://github.com/BerriAI/litellm (12,000+ Github Stars)
An integrated No-Code AI development suit which combines LangChains robust framework with Flowise intuitive low-code tools, empowering developers to accelerate development, testing, and deployment of advanced AI & LLM-powered applications.
No-code, multi-agent, multi-LLM generative AI orchestration platform for Corporate Knowledge Bases, Databases, Ticket Systems, Messaging Platforms, Cloud Storage Drives, Webpages, Virtual Agents, and more - with your choice of Large Language Model (LLM)
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.