updates

Author: jaschadub

blog/_layouts/default.html

@@ -29,10 +29,8 @@ <h1 class="site-name"><a href="{{ site.baseurl }}/">{{ site.name }}</a></h1>
 
             <nav>
               <a href="{{ site.baseurl }}/">Home</a>
-              <a href="{{ site.baseurl }}/getting-started">Getting Started</a>
               <a href="{{ site.baseurl }}/search">Search</a>
               <a href="{{ site.baseurl }}/about">About</a>
-              <a href="{{ site.baseurl }}/archive">Archive</a>
             </nav>
           </header>
         </div>

blog/_pages/about.md

@@ -4,26 +4,83 @@ title: About
 permalink: /about/
 ---
 
-[Reverie](https://github.com/amitmerchant1990/reverie) is a Jekyll theme which is simple and opinionated. It's actually a fork of [jekyll-now](https://github.com/barryclark/jekyll-now) with some additional features and personal touches which I've implemented to suit my needs for [my blog](https://www.amitmerchant.com).
-
-This is a plug-and-play Jekyll theme which you can use on GitHub Pages without even setting up a local environment.
-
-## Features
-
-- Command-line free fork-first workflow, using GitHub.com to create, customize and post to your blog
-- Fully responsive and mobile optimized base theme
-- Sass/Coffeescript support using Jekyll 2.0
-- Free hosting on your GitHub Pages user site
-- All the SEO goodies comes in-built
-- Markdown blogging
-- Syntax highlighting using Pygments
-    - [Dracula syntax theme](https://draculatheme.com/) included
-- Disqus commenting
-- Google Analytics integration
-- Fuzzy search across blog posts
-- Pagination of posts works out-of-the-box.
-- Categorize posts out-of-the box
-- RSS Feed
-- In-built sitemap
-
-Learn more about it [here](https://github.com/amitmerchant1990/reverie) on how to get started.
+# About ThirdKey Research
+
+ThirdKey Research is dedicated to advancing AI security through our "Zero Trust for AI" approach. We believe that **every AI interaction should be verified, every model should be validated, and every decision should be auditable**.
+
+## Our Mission
+
+As artificial intelligence becomes increasingly integrated into critical systems and decision-making processes, the need for robust security frameworks has never been more urgent. Traditional security models that rely on perimeter defense are insufficient for the dynamic, distributed nature of AI systems.
+
+We focus on extending Zero Trust principles to artificial intelligence systems, applying the philosophy of "never trust, always verify" to AI interactions, model behavior, and system integrity.
+
+## Research Projects
+
+### SchemaPin
+**Cryptographic Security for AI Tool Schemas**
+
+A cryptographic protocol for ensuring the integrity and authenticity of tool schemas used by AI agents. SchemaPin prevents "MCP Rug Pull" attacks by enabling developers to cryptographically sign their tool schemas and allowing clients to verify that schemas have not been altered since publication.
+
+- **Website**: [schemapin.org](https://schemapin.org)
+- **Features**: ECDSA P-256 signatures, Trust-On-First-Use key pinning, cross-language support
+- **License**: MIT
+
+### VectorSmuggle
+**Vector-Based Data Exfiltration Research**
+
+A comprehensive proof-of-concept demonstrating vector-based data exfiltration techniques in AI/ML environments. This project illustrates potential risks in RAG systems and provides tools and concepts for defensive analysis.
+
+- **Repository**: [github.com/jaschadub/VectorSmuggle](https://github.com/jaschadub/VectorSmuggle)
+- **License**: MIT
+- **Requirements**: Python 3.11+
+
+**Key Features:**
+- 🎭 **Steganographic Techniques**: Embedding obfuscation and data hiding
+- 📄 **Multi-Format Support**: Process 15+ document formats (PDF, Office, email, databases)
+- 🕵️ **Evasion Capabilities**: Behavioral camouflage and detection avoidance
+- 🔍 **Enhanced Query Engine**: Data reconstruction and analysis
+- 🐳 **Production-Ready**: Full containerization and Kubernetes deployment
+- 📊 **Analysis Tools**: Comprehensive forensic and risk assessment capabilities
+
+### AgentNull
+**AI System Security Threat Catalog + Proof-of-Concepts**
+
+A comprehensive security research project focused on cataloging and demonstrating threats specific to AI systems, providing both theoretical frameworks and practical proof-of-concepts for AI security vulnerabilities.
+
+- **Repository**: [github.com/jaschadub/AgentNull](https://github.com/jaschadub/AgentNull)
+- **Focus**: AI system security threats, attack vectors, and defensive strategies
+
+## Research Areas
+
+Our current research spans several critical domains:
+
+### Agent-Tool Interface Security
+- Cryptographic verification of tool schemas and integrity
+- Secure communication protocols between AI agents and external tools
+- Trust establishment and key management for agent-tool interactions
+- Prevention of tool substitution and schema manipulation attacks
+
+### Model Security
+- Adversarial robustness and defense mechanisms
+- Model integrity verification and tamper detection
+- Secure model deployment and distribution
+
+### AI Governance
+- Automated compliance monitoring for AI systems
+- Risk assessment frameworks for AI deployment
+- Ethical AI decision-making protocols
+
+### Threat Intelligence
+- AI-specific attack vectors and mitigation strategies
+- Emerging threats in the AI ecosystem
+- Security implications of AI advancement
+
+## Contact
+
+- **Email**: research@thirdkey.ai
+- **GitHub**: [ThirdKeyAI](https://github.com/ThirdKeyAI)
+- **Twitter**: [@ThirdKeyAI](https://twitter.com/ThirdKeyAI)
+
+---
+
+*ThirdKey Research is committed to advancing the state of AI security through open research and collaboration. Follow our work and join the conversation about building a more secure AI future.*