Ultraviolet Logo

Ultraviolet Blog

Technical articles, product updates, and engineering deep dives from the Ultraviolet team on building open-source confidential computing & secure AI Platforms.

PRISM AI: Architecting a Cost-Effective Cloud-Native AI Platform with Kubernetes and GitOps
Featured

PRISM AI: Architecting a Cost-Effective Cloud-Native AI Platform with Kubernetes and GitOps

Explore the DevOps and Kubernetes architecture powering Prism AI, a confidential computing platform that enables secure collaborative AI workloads.

Jilks Smith

Jilks Smith

May 4, 2026 · 9 min

prism ai kubernetes gitops devops cloud-native argocd devsecops
Beyond the Identity Crisis: Level 2 Binding in Cocos aTLS

Beyond the Identity Crisis: Level 2 Binding in Cocos aTLS

We've overhauled our attested TLS implementation to achieve Level 2 session binding, formally mitigating the relay attack vulnerabilities identified at IETF SEAT.

Sammy OinaDanko Miladinovic

Sammy Oina, Danko Miladinovic

March 27, 2026 · 6 min

confidential-computing attestation aTLS security
Cube AI Public Beta: The Future of Confidential LLM Inference is Here
announcement

Cube AI Public Beta: The Future of Confidential LLM Inference is Here

We are incredibly excited to announce the public beta release of Cube AI. Unlock the power of open-source, hardware-secured generative AI. Build and deploy agentic workflows with absolute data privacy using Trusted Execution Environments.

sammy oina

sammy oina

March 4, 2026 · 5 min

confidential-computing ai privacy cube ai
TLS and TEEs: Cocos AI Attested TLS — Design, Limitations, and the Path Forward

TLS and TEEs: Cocos AI Attested TLS — Design, Limitations, and the Path Forward

A rigorous look at Cocos AI's attested TLS implementation, the relay attacks identified by formal analysis at IETF SEAT, and what we plan to do about them.

Danko MiladinovicJovan DjukicSammy Oina

Danko Miladinovic, Jovan Djukic, Sammy Oina

February 27, 2026 · 18 min

confidential-computing attestation aTLS cocos ai
AMD SEV-SNP vs Intel TDX: Understanding TEE Support in Cube AI

AMD SEV-SNP vs Intel TDX: Understanding TEE Support in Cube AI

A technical comparison of AMD SEV-SNP and Intel TDX confidential computing technologies, and how Cube AI abstracts their complexities to provide a unified, secure platform for AI workloads.

sammy oina

sammy oina

February 24, 2026 · 5 min

security confidential-computing amd intel
Securing Trust: RATS and Attested TLS (aTLS)

Securing Trust: RATS and Attested TLS (aTLS)

COCOS AI leverages modern attestation standards to prove the integrity and operational state of the platform.

Jovan Djukic

Jovan Djukic

February 19, 2026 · 10 min

confidential-computing attestation aTLS cocos ai
The Privacy Paradox: Why AI Teams Should Care About Confidential Computing
blog

The Privacy Paradox: Why AI Teams Should Care About Confidential Computing

AI teams face a growing privacy paradox: they must process highly sensitive data at cloud scale while traditional architectures leave data in use exposed. This post explains how confidential computing and TEEs close that gap for enterprise AI workloads.

Jilks Smith

Jilks Smith

February 16, 2026 · 9 min

confidential-computing ai-security privacy tee
Prism AI Public Beta: Empowering Secure AI Collaboration
announcement

Prism AI Public Beta: Empowering Secure AI Collaboration

We are thrilled to announce the public beta release of Prism AI, our confidential computing platform for secure AI collaboration. Build and deploy privacy-preserving AI with hardware-verified security.

sammy oina

sammy oina

February 12, 2026 · 4 min

confidential-computing ai privacy prism ai
vLLM vs Ollama in Cube AI: Choosing the Right LLM Backend for Your Use Case

vLLM vs Ollama in Cube AI: Choosing the Right LLM Backend for Your Use Case

Compare vLLM and Ollama as pluggable LLM backends in Cube AI, and learn how to choose the right engine for your latency, throughput, cost, and deployment requirements.

Washington Kamadi

Washington Kamadi

February 11, 2026 · 18 min

architecture devops inference vllm
Unleashing Confidential AI: Cocos v0.8.0 and Prism v0.6.0 Released

Unleashing Confidential AI: Cocos v0.8.0 and Prism v0.6.0 Released

Ultraviolet releases Cocos AI v0.8.0 and Prism v0.6.0, enhancing the confidential computing ecosystem. These updates bring improved attestation, stronger security, and a better enterprise experience.

sammy oina

sammy oina

February 6, 2026 · 5 min

confidential-computing ai cocos ai prism ai
Confidential Computing Meets AI: How Cube AI Protects Your LLM Prompts

Confidential Computing Meets AI: How Cube AI Protects Your LLM Prompts

Cube AI leverages confidential computing and TEEs to protect your sensitive AI workloads. Ensure your prompts remain private with hardware-verified security.

sammy oina

sammy oina

January 30, 2026 · 5 min

security confidential-computing ai privacy
Categories
Ultraviolet

Ultraviolet is a leading company specializing in confidential computing, cloud security, AI/ML, multi-party computation, and secure data sharing.

Connect with us
Subscribe to Our Newsletter

Stay updated with the latest news, updates and announcements.