All Episodes

Claude Mythos Project Glasswing Ai Safety Capabilities

Xss Cross Site Scripting Persistent Web Vulnerability

Pass The Hash Credential Free Lateral Movement Windows

Kubernetes Pod Escape Cloud Takeover

Supply Chain Attacks Solarwinds Playbook Revisited

Securing Hybrid Enterprise Layered Defense Architecture

Living Off The Land Lotl Attacks Weaponizing Built In Os Tools

Business Email Compromise Social Engineering Attack Deep Dive

Ssrf Pivoting Through Your Own Infrastructure

Kerberoasting Extracting Service Account Credentials Active Directory

Double Extortion Ransomware Anatomy Kill Chain

Sql Injection 2025 Undying King Web Exploitation

Agentic Ai Exploitation Tool Abuse Goal Manipulation

Goal Misgeneralization Ai Pursues Wrong Objective

Reward Hacking Manipulating Reinforcement Learning Systems

Ml Framework Dependency Attacks Pytorch Tensorflow

Pickle File Attacks Weaponizing Ai Model Weights

Model Watermark Removal Destroying Ip Protection

Adversarial Examples Fooling Ai Imperceptible Perturbations

Model Extraction Stealing Ai Models Api Queries

Training Data Memorization Llm Leak Secrets

Membership Inference Attacks Proving Data In Training Set

Gradient Inversion Reconstructing Private Data From Model Updates

Model Supply Chain Poisoning Trojan Horse Ai Pipeline

Rag Poisoning Corrupting Knowledge Base Ai Trusts

Attacking Ml Api Gateways Behavioral Drift Model Poisoning

Federated Learning Poisoning Weaponizing Collaborative Ai

Backdoor Attacks Trojaned Neural Networks

Clean Label Poisoning Invisible Training Data Attack

Payload Splitting Bypassing Ai Filters

Multi-Turn Manipulation: The Slow Burn Attack That Bypasses Every Single-Turn Defense

Invisible Commands: Visual Prompt Injection Against Multimodal LLMs

Building Your Own Vulnerable AI Agent: A Complete LangChain + Ollama Attack Lab

RAG Poisoning: Weaponizing Vector Databases to Hijack LLM Outputs

Building Your AI Attack Lab: Local LLM Pentesting from Zero to Pwned

Token Smuggling: When Your Tokenizer Becomes the Attack Vector

Jailbreaking LLMs: The Art of Breaking AI Safety at Scale

Indirect Prompt Injection: Weaponizing the Web Against Your AI

Budgeting for AI Security: Where CISOs Should Invest in 2026

Securing AI Training Data Pipelines: A Practitioner's Guide to Protecting Your Model's Foundation

AI Vendor Risk Management: What CISOs Must Demand Before Signing the Contract

AI Security Posture Management: Navigating the Emerging Standards Landscape in 2026

AI Model Watermarking and IP Protection: Defending Your Neural Networks from Theft

AI Governance Frameworks: From Policy to Practice

AI Risk Assessment Frameworks for CISOs: Building Board-Ready Governance

AI Risk Assessment Frameworks for CISOs: Building Board-Ready Governance in the Age of Machine Learning

Securing AI APIs: Beyond Rate Limiting — A Defense-in-Depth Architecture for the LLM Era

AI Risk Assessment Frameworks for CISOs: Enterprise Governance Playbook

Model Inversion Attacks: How Adversaries Extract Your Training Data from LLMs

The Silent Siphon: How AI Chatbots Become Enterprise Data Exfiltration Vectors

AI-Assisted Red Teaming: Weaponizing Machine Learning Before Your Adversaries Do

Fortress RAG: A Security Architect's Guide to Hardening Retrieval-Augmented Generation Pipelines

AI-Generated Deepfakes for Business Email Compromise: The $4.7B Threat Evolving Faster Than Your Defenses

AI-Powered Phishing: The Next Generation of Social Engineering

Adversarial Machine Learning: The Art of Fooling AI Security Tools

Securing AI in Healthcare: When HIPAA Meets Machine Learning and Nobody's Ready

Operationalizing the NIST AI RMF: A Battle-Tested Implementation Guide for Security Architects

LLM Output Sanitization: Preventing Code Injection When Your AI Writes Code

Zero-Trust Architecture for AI/ML Infrastructure: Building Defenses for the Neural Age

AI Governance for CISOs: Turning Policy into Practice

Breaking the Guardrails: LLM Jailbreaking Techniques and Enterprise Defense Strategies

The CISO's Guide to AI Risk: What Boards Are Really Asking (And How to Answer Them)

Federated Learning Security: When Collaboration Becomes Risk

Agentic AI Security: When AI Agents Go Rogue and How to Stop Them

AI Shadow IT: The Invisible Threat Multiplier in Your Enterprise

AI Model Supply Chain Poisoning: The Silent Threat Lurking in Your ML Pipeline

Prompt Injection Attacks on Enterprise AI Assistants: The Invisible Threat in Your LLM Deployments