Sold by: Waltsoft Inc.
Deployed on AWS
protectai/deberta-v3-base-prompt-injection-v2 on SageMaker. Binary classifier detecting prompt injection and jailbreak attempts before they reach your LLM. ~20-40ms latency, ~95% accuracy, $0.08/hr.
Overview
Prompt Injection Detector v2 from Protect AI is a fine-tuned DeBERTa-v3-base model that classifies text as SAFE or INJECTION with ~95% accuracy on held-out prompt injection and jailbreak datasets. It catches direct injection (embedded instructions in user input), indirect injection (malicious content in retrieved documents), and jailbreak patterns before they reach your language model.
Deploy as a SageMaker endpoint to screen every message entering your LLM pipeline. At 20-40ms per classification on ml.m5.xlarge, it adds negligible latency to real-time chat and agent workflows. Unlike Amazon Bedrock Guardrails, this endpoint works in front of any LLM -- Claude, GPT-4 via API gateway, self-hosted Llama, or any custom model -- making it a model-agnostic security layer.
The endpoint accepts a single text string and returns {"label": "SAFE" | "INJECTION", "score": 0.0-1.0}. Integrate as middleware in your agent orchestration layer, API gateway, or Lambda function.
Primary use cases: enterprise AI assistant security gates, RAG pipeline input filtering, multi-tenant LLM API protection, customer-facing chatbot guardrails, and any architecture where user-supplied text reaches a language model.
Highlights
- ~95% accuracy on prompt injection and jailbreak detection -- model-agnostic, protects Claude, GPT-4, Llama, or any LLM endpoint
- 20-40ms per classification on ml.m5.xlarge -- negligible overhead for real-time chat and agent pipelines
- Flat $0.08/hr, SAFE/INJECTION label plus confidence score -- no per-call charges, all inference in your AWS VPC
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
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.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.10 |
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $0.10 |
Vendor refund policy
No refunds.
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
Initial release
Additional details
Inputs
- Summary
protectai/deberta-v3-base-prompt-injection-v2 on SageMaker. Binary classifier detecting prompt injection and jailbreak attempts before they reach your LLM. ~20-40ms latency, ~95% accuracy, $0.08/hr.
- Input MIME type
- application/json
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
Support
Vendor support
Contact support@waltsoft.net for deployment assistance.
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
Empower your organization to safely and securely embrace AI.
This solution generates an image from scratch incorporating elements described in the text prompt.
Fooocus is a re-imagination of how Image generation models work, go from prompt to high fidelity images in seconds.
This is a repackaged open source software product wherein additional charges apply for support while launching it and connecting to the instance for the first time as well as continuous security updates available in new versions.
One of the most customizable and accessible image models available, maintaining top-tier performance in prompt adherence and image quality.
Accelerate innovation at AI scale by using LaunchDarkly for your front-end and back-end feature releases on AWS, including AI applications using Amazon Bedrock and AgentCore!
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.