Prompt Injection and Jailbreaks
This chapter examines prompt injection and jailbreak attacks, which exploit a language model's inherent inability to distinguish between authoritative developer instructions and untrusted user data. I...
7 Jul 45min
Threat Modeling for LLM Systems
This chapter adapts traditional threat modeling frameworks (such as STRIDE, PASTA, and attack trees) specifically for the unique vulnerabilities of LLM systems. It guides defenders through identifying...
6 Jul 54min
Why AI Security Is Different
This chapter explains that AI security fundamentally and structurally differs from traditional software security. Instead of finding and patching clear bugs in readable source code, defenders must sec...
6 Jul 49min
2-7-7. Hallucinations and Reliability: Managing Confident Errors
This episode covers Chapter 7, examining why Large Language Models confidently generate false information. We discuss the probabilistic nature of "hallucinations," the dangerous gap between fluency an...
19 Feb 16min
2-7-6. Retrieval-Augmented Generation Risks: Securing the Knowledge Pipeline
This episode covers Chapter 6, focusing on the security implications of connecting models to external data (RAG). We discuss how this introduces new trust boundaries, the dangers of malicious document...
19 Feb 34min
2-7-5. Input Validation and Output Filtering: The Defense Pipeline
This episode covers Chapter 5, detailing how to build disciplined pipelines around an AI model. We discuss strategies for sanitizing user inputs to catch attacks early, the importance of structured pr...
18 Feb 29min
2-7-4. Prompt Injection and Jailbreaks: Defending the Interpreter
This episode explores Chapter 4, detailing how attackers manipulate model behavior through crafted inputs like instruction overrides. We discuss why prompt injection is an inherent property of instruc...
18 Feb 37min
