This video provides a tutorial on using Garrick, a large language model vulnerability scanner, to test custom chat bots. Garrick employs probes (test cases) and detectors to identify vulnerabilities, drawing from a large, constantly updated probe library. The tutorial focuses on testing a simple chat application called Wy chat, which utilizes Llama 3 and the Read More …
Tag: nvidia
Month of AI Video – Practical LLM Security
Practical LLM Security As large language models (LLMs) become increasingly integrated into various applications, the security standards for these integrations have not kept pace. Much of the current security research tends to focus on either 1) the social harms and biases associated with LLMs, along with content moderation issues, or 2) the LLMs themselves, often Read More …