GenAI Protector Plus is an advanced GenAI firewall designed to secure your GenAI applications with intelligent GenAI guardrails. Backed by our proprietary ShieldPrompt™ technology, it provides adaptive AI security that protects against prompt injection attacks, data breaches, and malicious activities.
In an AI-driven world, security is not just about protecting networks, it is about safeguarding the confidentiality, integrity and availability of your generative AI applications. This is where our GenAI Protector Plus fits in. As a GenAI firewall, it is powered by GPU and serves as a security control gateway between your AI applications and potential threats such as prompt injection attacks, system prompt leakage, sensitive data leakage and other OWASP Top 10 for LLM threats
Highlights
Multi-Layered ShieldPrompt™ Defence: Safeguarding your GenAI applications from sophisticated threats is no small task. That is why ShieldPrompt™, developed by our AI Security tech experts, leverages multiple security techniques in tandem to enhance defence precision through contextual understanding, delivering robust protection for your GenAI applications.
Threat Vector Database: Threat intelligence database with updated insights to detect emerging malicious prompts through semantic similarity analysis.
CyberLLM: Uses a LLM model specifically designed to detect malicious intent in the user input prompts.
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 is based on a fixed subscription cost and actual usage of the product. You pay the same amount each billing period for access, plus an additional amount according to how much you consume. The fixed subscription cost is prorated, so you're only charged for the number of days you've been subscribed. 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.
You pay by the hour for the compute instance that runs this GenAI firewall. The six options are AWS EC2 instance types, not feature tiers. Four are GPU-backed instances (g6.2xlarge, g6e.2xlarge, g6e.4xlarge, g6e.8xlarge), which suit the GPU-based threat analysis. Two are memory-optimized instances (r5.2xlarge, r6i.2xlarge). Your cost scales with the instance size and how many hours you run it. Larger instances add compute capacity for higher traffic. Every instance delivers the same software protection; you choose based on performance needs and expected load.
Top-of-mind questions for buyers
What do the GPU-backed instances give me over the memory-optimized ones for this firewall?
The GPU instances (g6 and g6e types) provide graphics-processing acceleration. This firewall uses GPU-based analysis to inspect prompts and outputs in real time. The memory-optimized instances (r5.2xlarge, r6i.2xlarge) supply more RAM instead. You choose the instance based on your expected traffic and performance needs.
Am I charged when the instance is stopped or paused?
You pay the hourly software rate only while the instance runs. A fully stopped instance stops accruing software charges. Note that underlying AWS storage or resources tied to a stopped instance may still incur separate AWS fees. The firewall software meters running hours only.
If my traffic grows, do I upgrade automatically or do I switch instances myself?
There is no automatic tier upgrade. Each option is a separate AWS EC2 instance type you select and run. To handle higher traffic, you choose a larger instance or run additional instances yourself. Your cost then reflects the new instance size and the hours you run it.
Request a private offer to receive a custom quote.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Overview
Protector Plus is a GPU-powered GenAI firewall engineered to provide advanced security for generative AI applications and LLM-based chatbots. Acting as a proactive gatekeeper, it delivers robust defense against sophisticated threats targeting AI systems.
Advance Features
Content Moderation
Automatically detects and blocks hazardous content in both user prompts and AI-generated outputs, ensuring safe and responsible AI interactions.
System Prompt Protection
Identifies and prevents the leakage of system-level instructions, safeguarding your core application logic.
Threat Vector Database
Integrates a continuously updated threat intelligence database, using semantic similarity analysis to recognize and stop emerging malicious prompts.
CyberLLM
Employs a dedicated LLM model tailored to detect and flag malicious intent in user input prompts, providing another layer of AI-driven security.
Additional details
Usage instructions
Launch the Instance
Deploy the Protector Plus AMI. Once deployed, navigate to your AWS EC2 Dashboard to find the running instance.
Note down the public IP address and the Instance ID of your Protector Plus VM.
Access the Web UI
Open your browser and go to: https://<Public-IP-Address>:3000
Login credentials:
Username: admin
Password: Adm1n-i-<Instance-ID>
(Replace <Public-IP-Address> and <Instance-ID> with the instance actual values.)
3.Access via CLI (SSH)
Connect to the instance over SSH using the following:
Username: kioskuser
Password: ku-<Instance-ID>
(Replace <Instance-ID> with your actual instance ID.)
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.
Discover the limitless possibilities of Generative AI (GenAI) on AWS. The PREDICTif GenAI workshop will help you unlock the potential of GenAI to drive business growth. Leverage PREDICTif's expertise and experience to confidently embark on a transformative journey.
Consider this your MVG - Minimum Viable Generative AI. Engage in a hands-on generative AI workshop and leave with a practical LLM deployment strategy, tailored to your unique data and privacy needs. AWS covers 100% of the cost for startup customers.
The world of Generative AI (GenAI) is rapidly evolving, offering exciting possibilities for content creation and automation. AllCloud’s GenAI Proof of Concept (POC) Implementation allows you to experiment with the power of GenAI in a low-risk environment, demonstrating its potential for a targeted use case within your organization.
Trellix Helix unifies threat events across the security stack and applies AI-driven analytics, alert triage, and automation to accelerate detection, investigation, and response. By correlating data from Trellix and 500+ third-party tools, Helix reveals the full attack story while reducing manual pivots and analyst workload. Key capabilities include AI-driven detection and triage, no-code hyperautomation for investigation and response, and an open integration ecosystem that supports cloud, hybrid, and air-gapped deployments.
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.