Update README.md

README.md

@@ -6,61 +6,78 @@ sdk: static
 pinned: false
 ---
 
-# Neuralchemy
+# Neuralchemy Research
 
-**AI Security • Prompt Defense • LLM Safety**
+**AI Security · Autonomous Systems · LLM Safety**
 
-Building secure, reliable AI systems focused on prompt security, adversarial robustness, and practical safety tooling.
+Independent research lab building open datasets, 
+models, and frameworks for LLM security and 
+autonomous evaluation.
 
 ---
 
-##  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.
+## Research Papers
 
-### Core Resources
+**AI In The Loop (AITL): A Systems Taxonomy 
+for Closed-Loop Autonomous Evaluation**
+Sanskar Jajoo · Neuralchemy Labs · 2026
+[zenodo.org/records/19551173](https://zenodo.org/records/19551173)
 
-* **SOTA Datasets:**
-  [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).
+**The Autonomous Sunk-Cost Fallacy: Stopping 
+Failures and Meta-Reasoning in LLMs Deployed 
+within AEOS**
+Sanskar Jajoo · Neuralchemy Labs · 2026
+[zenodo.org/records/19846960](https://zenodo.org/records/19846960)
 
-  [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. 
+## Datasets
 
-* **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.
+**Prompt Injection Threat Matrix**
+32,320 samples · 7 intent classes · 
+10 severity levels · Full threat schema
+[View Dataset](https://huggingface.co/datasets/neuralchemy/prompt-injection-Threat-Matrix)
 
-* **Live Demo Space:** [Prompt-injection-DeBERTa](https://huggingface.co/spaces/neuralchemy/Prompt-injection-DeBERTa)
-  Interactive inference demo for prompt safety classification.
+**Prompt Injection Dataset**
+6,000+ samples · Benign vs malicious · 
+Real-world attack scenarios
+[View Dataset](https://huggingface.co/datasets/neuralchemy/prompt-injection-dataset)
 
 ---
 
-## Research & Architecture
+## Models
 
-* **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.
-  https://zenodo.org/records/19551173
-
-  **The Autonomous Sunk-Cost Fallacy: Stopping Failures and Meta-Reasoning in LLMs Deployed within the Autonomous Empirical Optimization System (AEOS)**
-  https://zenodo.org/records/19846960
----
+**DistilBERT Threat Matrix Classifier**
+99.4% F1 · Prompt intent classification · 
+High-speed inference
+[View Model](https://huggingface.co/neuralchemy/distilbert-base-threat-matrix)
 
-##  Mission
+**DeBERTa Prompt Injection Classifier**
+Transformer-based injection detection
+[View Model](https://huggingface.co/neuralchemy/prompt-injection-deberta)
 
-Advancing AI security through enterprise open-source datasets, robust model deployment, and adversarial safety research.
+**Classical ML Detector**
+Lightweight RF/LR classifiers for 
+offline/legacy deployment
+[View Model](https://huggingface.co/neuralchemy/prompt-injection-detector)
 
 ---
 
-##  Connectivity
-
-* **Website:** https://www.neuralchemy.in
+## Live Demo
 
+Try our prompt injection classifier:
+[Prompt-injection-DeBERTa Space](https://huggingface.co/spaces/neuralchemy/Prompt-injection-DeBERTa)
 
 ---
 
-*Building safer AI systems through open security research.* 🚀
+## About
+
+NeuralAlchemy is an independent AI security 
+research lab based in India. We build open 
+datasets, train security models, and publish 
+research on LLM behavioral failures and 
+autonomous evaluation systems.
+
+**Website:** neuralchemy.in
+**GitHub:** github.com/m4vic
+**Contact:** Via GitHub or neuralchemy.in