Episode 39 - The Dark Side of MCP: How LLMs Can Be Hacked by Design

Short Story by a Small Agent Model (SAM)

Welcome to a unique storytelling experiment. What you're about to hear wasn't written in the traditional sense. It was generated entirely by SAM—the Small Agent Model—an AI trained on technical documents, research papers, and patterns pulled from a vast archive of open-access knowledge, including thousands of PDFs from arXiv.org. This story began with a single prompt and evolved entirely within SAM’s internal reasoning. No plot outline. No human editing. Just raw output shaped by the model’s logic, curiosity, and sense of narrative. Our goal? To test whether a small, locally-running AI could hold focus across a long-form story—maintaining character development, tension, and thematic consistency. The result is a digital hallucination… but one grounded in real science, speculative fiction, and machine-learned creativity. Let’s begin.

Episode 40 - Teaching Smaller AI Models to Think Like Cybersecurity Experts: A Deep Dive into Knowledge Distillation

In this episode, we unpack a cutting-edge approach to building lean, high-performance AI models tailored for cybersecurity. Based on our latest white paper, we explore a multi-stage knowledge distillation pipeline that transfers expertise from large teacher models to smaller, more efficient student models like Phi-3 Mini. Topics include structured data enrichment, virtual machine-based learning, test-time reinforcement learning (TTRL), and curiosity-driven exploration powered by Information Theory. Whether you're an AI researcher, cybersecurity professional, or tech strategist, this episode offers a deep yet accessible guide to making specialized AI practical for real-world, resource-constrained environments.

Episode 39 - The Dark Side of MCP: How LLMs Can Be Hacked by Design

The paper titled "MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits" by Brandon Radosevich and John Halloran investigates security vulnerabilities introduced by the Model Context Protocol (MCP), an open standard designed to streamline integration between large language models (LLMs), data sources, and agentic tools. While MCP aims to facilitate seamless AI workflows, the authors identify significant security risks associated with its current design.

Episode 38 - Unmasking Cyber Threats: Agentless Emulation for Next-Gen Cyber Defense

In this episode, we explore how modern cybersecurity is transforming with agentless threat emulation. We discuss a cutting-edge platform that simulates advanced persistent threat (APT) tactics without installing agents—leveraging open-source tools like Atomic Red Team and PurpleSharp alongside the MITRE ATT&CK framework. Discover how the platform’s user-friendly, drag-and-drop scenario builder, remote execution via SSH/WinRM, and real-time monitoring empower cyber defenders to train effectively, identify detection gaps, and bolster overall security. Join us as we break down the technical innovations, operational benefits, and strategic value of continuous, automated threat simulations in today’s dynamic cyber landscape.

Episode 37 - NIST Report on Adversarial Machine Learning Taxonomy and Terminology

This NIST report offers a comprehensive exploration of adversarial machine learning (AML), detailing threats against both predictive AI (PredAI) and generative AI (GenAI) systems. It presents a structured taxonomy and terminology of various attacks, categorising them by the AI system properties they target, such as availability, integrity, and privacy, with an additional category for GenAI focusing on misuse enablement. The document outlines the stages of learning vulnerable to attacks and the varying capabilities and knowledge an attacker might possess. Furthermore, it describes existing and potential mitigation strategies to defend against these evolving threats, highlighting the inherent trade-offs and challenges in securing AI systems.