Protopia AI is at RSAC. Meet our team of experts in AI Data Privacy and Security.
Government and defense agencies face unique challenges when it comes to AI data access and data protection. Enable timely access to insights using the best AI algorithms without compromising sensitive information.
Stained Glass Transform can be used to analyze video and image data for security purposes while protecting the identities of individuals in the images.
Agencies look to share intelligence insights without exposing underlying data to each other in unprotected/human-understandable representations.
When training or using ML models for Detection and Response (MLDR), neither the training data nor the data used for predictions need to be exposed. Maximizing protection for your network data should be essential to your MLDR cybersecurity strategy.
Protopia AI partnered with NetApp and implemented Stained Glass Transform™ to demonstrate the breakthrough capability of being able to perform a task like real-time face recognition of VIPs without exposing unprotected images. This capability was showcased at the annual Trident Warrior exercise.
The solution transformed subjects’ faces into Randomized Re‑Representations that were only readable by the facial recognition model with near‑perfect accuracy to identify VIPs. The use case showcased Stained Glass’ ability to protect real-time AI deployment successfully.
Protopia AI Receives $1.25M Direct-to-Phase II Contract from U.S. Air Force to Demonstrate Stained Glass Transform In partnership with the
Available through Amazon SageMaker and AWS Marketplace, Protopia Stained Glass Transform (SGT) adds a drop-in privacy layer to protect critical data in enterprise AI applications. SGT enables secure inference on open-weight models, starting with Llama 3.1 8B, and is designed to support high-impact use cases like RAG, document processing, and customer interaction, especially in industries where sensitive or proprietary data would otherwise block adoption.
Protopia now supports vLLM’s new prompt embedding feature, enabling secure LLM inference without plaintext at inference. Together, vLMM and Protopia Stained Glass Transforms (SGTs) unlock private, high-performance AI workloads for enterprises handling sensitive data.