References

Machine Learning

• SANS SEC495: Practical Use of AI and Large Language Models for Cybersecurity (https://www.sans.org/cyber-security-courses/leveraging-llms-building-securing-rag/)
• Agentic Retrieval-Augmented Generation: A Survey On Agentic Rag (https://arxiv.org/pdf/2501.09136)
• Automating Threat Intelligence Analysis with Retrieval Augmented Generation (RAG) for Enhanced Cybersecurity Posture (https://www.researchgate.net/publication/380422422_Automating_Threat_Intelligence_Analysis_with_Retrieval_Augmented_Generation_RAG_for_Enhanced_Cybersecurity_Posture)
• CyKG-RAG: Towards knowledge-graph enhanced retrieval augmented generation for cybersecurity (https://2025.rage-kg.org/papers/RAGE-KG_2024_paper_1.pdf)
• From Hallucinations to Reality: A Critical Examination of LLM-Based Alert Investigation Tools (https://files.abstractsonline.com/CTRL/7A/2/54D/D87/B3B/407/CBF/E61/6CD/813/EF8/CA/a283_1.pdf)
  • Hallucinations to Reality Github Repository (https://github.com/akul-goyal/Hallucinations-to-Reality)
• One Hot Encoding in Machine Learning (https://www.geeksforgeeks.org/ml-one-hot-encoding/)
• Keras Layer Weight Initializers (https://keras.io/api/layers/initializers/)
• Weight Initialization for Deep Learning Neural Networks (https://machinelearningmastery.com/weight-initialization-for-deep-learning-neural-networks/)
• AI Essentials: What are model weights? (https://www.engine.is/news/category/ai-essentials-what-are-model-weights)
• What are embeddings in machine learning? (https://www.cloudflare.com/learning/ai/what-are-embeddings/)
• Understanding GPT tokenizers (https://simonwillison.net/2023/Jun/8/gpt-tokenizers/)
• tf.TensorSpec (https://www.tensorflow.org/api_docs/python/tf/TensorSpec)

Vector Databases and Data Formatting

• Vector database management systems: Fundamental concepts, use-cases, and current challenges (https://www.sciencedirect.com/science/article/pii/S1389041724000093)
• Milvus: A Purpose-Built Vector Data Management System (https://dl.acm.org/doi/pdf/10.1145/3448016.3457550)
• Ingest Data to Vector Database: Milvus Example (https://www.decube.io/post/ingest-data-vector-database-milvus)
• Ingesting Chaos: The MLOps Behind Handling Unstructured Data Reliably at Scale for RAG (https://milvus.io/blog/Ingesting-Chaos-MLOps-Behind-Handling-Unstructured-Data-Reliably-at-Scale-for-RAG.md)
• SBERT: Sentence Transformers - Pretrained Models (https://www.sbert.net/docs/sentence_transformer/pretrained_models.html)
• Run Milvus with Docker Compose (Linux) (https://milvus.io/docs/install_standalone-docker-compose.md)
• Mastering Chunking Strategies with the Art and Science of Chunking for High-Performance AI-RAG Systems. (https://medium.com/@ranabidwh/mastering-chunking-strategies-with-the-art-and-science-of-chunking-for-high-performance-ai-rag-31257a906e72)
• How to Evaluate Retrieval Augmented Generation (RAG) Systems (https://www.ridgerun.ai/post/how-to-evaluate-retrieval-augmented-generation-rag-systems)
• Classification: Accuracy, recall, precision, and related metrics (https://developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall)

MS Graph

• Build Python apps with Microsoft Graph (https://learn.microsoft.com/en-us/graph/tutorials/python?tabs=aad)
• Microsoft Graph List joinedTeams API Endpoint (https://learn.microsoft.com/en-us/graph/api/user-list-joinedteams?view=graph-rest-1.0&tabs=python)
• Microsoft Graph List channels API Endpoint (https://learn.microsoft.com/en-us/graph/api/channel-list?view=graph-rest-1.0&tabs=http)
• Microsoft Graph List channel messages API Endpoint (https://learn.microsoft.com/en-us/graph/api/channel-list-messages?view=graph-rest-1.0&tabs=python)