Update README.md

README.md

@@ -8,4 +8,100 @@ pipeline_tag: text-classification
 tags:
 - bert
 - guardrail
----
+---
+HomayShield: CPU-Based AI Guardrail for Turkish & English Security Filtering
+
+HomayShield is a lightweight CPU-based AI guardrail system designed to detect malicious, adversarial, and suspicious inputs targeting AI systems.
+
+The project focuses on providing practical AI security for organizations that cannot deploy GPU-heavy guardrail solutions.
+
+Supported languages:
+
+Turkish
+English
+Mixed Turkish-English prompts
+Why HomayShield?
+
+As AI adoption grows, organizations increasingly deploy:
+
+LLM applications
+Chatbots
+AI agents
+RAG systems
+Internal AI assistants
+Web-integrated AI pipelines
+These systems introduce new attack surfaces.
+
+Examples include:
+
+Prompt injection
+Jailbreak attacks
+Instruction override
+Data exfiltration
+Tool abuse
+Indirect prompt injection
+Modern guardrails often rely on LLM-based security analysis.
+
+These systems are powerful, but they introduce major operational challenges:
+
+High infrastructure cost
+GPU dependency
+High inference latency
+Expensive scaling
+Complex deployment
+Many small and mid-sized organizations cannot afford dedicated GPU infrastructure for security layers.
+
+This creates a major security gap.
+
+Project Goal
+
+HomayShield aims to provide a practical alternative.
+
+Main objectives:
+
+CPU-based inference
+Low latency
+No GPU requirement in production
+Easy enterprise deployment
+Lower operational cost
+Strong baseline AI security
+HomayShield is designed for:
+
+SOC environments
+Enterprise AI systems
+Air-gapped systems
+On-prem deployments
+CPU-only environments
+Important Note
+
+HomayShield is not intended to replace LLM-based guardrails.
+
+LLM guardrails typically provide:
+
+deeper reasoning
+better contextual understanding
+stronger zero-day detection
+more adaptive behavior
+In most scenarios, LLM-based guardrails are more powerful.
+
+However, HomayShield offers an important tradeoff:
+
+lower detection capability than advanced LLM guardrails
+significantly lower infrastructure cost
+much easier deployment
+much faster CPU inference
+For many organizations, deployability matters.
+
+A CPU-based guardrail is better than having no guardrail.
+Core Architecture
+
+HomayShield is built around one key principle:
+
+Run encoder once. Use output twice.
+A single shared encoder generates embeddings used by both:
+
+Semantic similarity detection
+Classifier prediction
+Architecture:
+![Screenshot 2026-06-26 at 14.30.30](https://cdn-uploads.huggingface.co/production/uploads/6720d6553279dd0ff66c4995/hqHqkwOQtg1lY0RTQdxxE.png)
+