Prompt Audit and Security: Engineering Defenses for LLM-Powered Systems
A practical engineering guide to securing LLM features: prompt injection defenses, audit logging, eval-driven red teaming, and the governance patterns teams need before launch.
Llm-Security
Poisoning Attacks on LLMs: How Adversaries Corrupt Models and What Defenders Can Do
Poisoning attacks corrupt the data, weights, or fine-tuning process of large language models. This post breaks down the attack surface, walks through recent incidents, and lays out the defenses working teams can ship today.