Securing LLMs: A Field Guide

A practitioner tour of the LLM attack surface — the OWASP LLM Top 10, MLSecOps pipelines, threat modeling, the AI supply chain, and emerging governance.

1. 1

   The OWASP Top 10 for LLMs: A Field Guide

   A field guide to the OWASP Top 10 for LLM Applications, the ten vulnerability categories that define modern AI application security.

2. 2

   Prompt Injection: The XSS of LLMs

   How prompt injection subverts large language models through direct and indirect input, why it has no clean fix, and the layered defenses that contain it.

3. 3

   Insecure Output Handling

   Why model output must be treated as untrusted input, how it becomes XSS, SSRF, and code execution downstream, and the encoding and validation that contain it.

4. 4

   Poisoning the Well: Training-Data Attacks

   How poisoned training data plants backdoors and bias in language models, where it enters the pipeline, and the defenses that catch it early.

5. 5

   Starving the Model: LLM Denial of Service

   Context-window exhaustion and denial-of-wallet attacks against LLM applications, and the rate limiting, input caps, and resource budgeting that contain them.

6. 6

   Three Quiet Killers: Sensitive Disclosure, Insecure Plugins, Excessive Agency

   Three under-discussed OWASP LLM risks: sensitive data leakage, insecure plugin design, and excessive agent autonomy, with mitigations for each.

7. 7

   Overreliance and the Hallucination Problem

   What LLM hallucinations are, why they happen, documented overreliance failures in law and code, and the mitigations that actually reduce the damage.

13 more articles coming soon.