Update README.md

README.md

@@ -6,8 +6,6 @@ sdk: static
 pinned: false
 ---
 
----
-
 # Neuralchemy
 
 **AI Security • Prompt Defense • LLM Safety**
@@ -16,45 +14,50 @@ Building secure, reliable AI systems focused on prompt security, adversarial rob
 
 ---
 
-## Featured Project — PromptShield
+##  Featured Project — PromptShield & Threat Matrix
+A comprehensive prompt injection and adversarial intent detection framework, classifying malicious jailbreak patterns across real-world and massive synthetic attack typologies.
 
-Prompt injection detection framework designed to classify benign vs malicious prompts across real-world and synthetic attack patterns.
+### Core Resources
 
-### Resources
+* **Datasets:**
 
-* **Dataset:** [neuralchemy/prompt-injection-dataset](https://huggingface.co/datasets/neuralchemy/prompt-injection-dataset)
-  6000+ prompt injection and benign samples collected from realistic attack scenarios.
+* [neuralchemy/prompt-injection-Threat-Matrix](https://huggingface.co/datasets/neuralchemy/prompt-injection-Threat-Matrix)
+  A highly curated, leakage-free classification dataset mapping 32,000+ entries across a 5-dimensional security ontology (Intent, Technique, Severity).
 
-* **ML Models:** [neuralchemy/prompt-injection-detector](https://huggingface.co/neuralchemy/prompt-injection-detector)
-  Classical machine learning classifiers for prompt risk detection.
+* [neuralchemy/prompt-injection-dataset](https://huggingface.co/datasets/neuralchemy/prompt-injection-dataset)
+  6000+ prompt injection and benign samples collected from realistic attack scenarios.
 
 * **DeBERTa Fine-Tuned Model:** [neuralchemy/prompt-injection-deberta](https://huggingface.co/neuralchemy/prompt-injection-deberta)
   Transformer-based prompt injection classifier.
 
+* **DistilBERT Base Model:** [neuralchemy/distilbert-base-threat-matrix](https://huggingface.co/neuralchemy/distilbert-base-threat-matrix)
+  A 99.4% F1-scoring Transformer defense gateway, optimized for high-speed, accurate prompt intent gating. 
+
+* **Classical ML Models:** [neuralchemy/prompt-injection-detector](https://huggingface.co/neuralchemy/prompt-injection-detector)
+  Ultra-lightweight machine learning classifiers (RF, LR) for legacy/offline prompt risk detection.
+
 * **Live Demo Space:** [Prompt-injection-DeBERTa](https://huggingface.co/spaces/neuralchemy/Prompt-injection-DeBERTa)
   Interactive inference demo for prompt safety classification.
 
 ---
 
-## Mission
+## Research & Architecture
 
-Advancing AI security through open datasets, practical model deployment, and adversarial safety research.
+* **AI In The Loop (AITL):**
+  Pioneering an inherently secure, multi-agent orchestration loop designed strictly to mitigate Prompt Injection (PI) bypass methodologies, enforce JSON-structured constraints, and evaluate autonomous systemic risks.
 
 ---
 
-## Focus Areas
+##  Mission
 
-* Prompt Injection Detection
-* Adversarial Prompt Benchmarking
-* LLM Safety Evaluation
-* Secure AI Tooling
+Advancing AI security through enterprise open-source datasets, robust model deployment, and adversarial safety research.
 
 ---
 
-## Links
+##  Connectivity
 
 * **Website:** https://www.neuralchemy.in
-* **GitHub:** https://github.com/neuralchemy
+
 
 ---