This post is part of the NVIDIA AI Red Team’s continuing vulnerability and technique research. Use the concepts presented to responsibly assess and increase…
This post is part of the NVIDIA AI Red Team’s continuing vulnerability and technique research. Use the concepts presented to responsibly assess and increase the security of your AI development and deployment processes and applications. Large language models (LLMs) don’t operate over strings. Instead, prompts are passed through an often-transparent translator called a tokenizer that creates an…