Large language model applications evaluate the sentence perplexity of user prompts to detect and mitigate adversarial suffixes designed to assist in the generation of sensitive or harmful content.
Topic
Secure software design and development
Applicable to
all
History
Jun 2024
Large language model applications evaluate the sentence perplexity of user prompts to detect and mitigate adversarial suffixes designed to assist in the generation of sensitive or harmful content.
A new control was added recommending that large language model applications evaluate the sentence perplexity of user prompts to detect and mitigate adversarial suffixes designed to assist in the generation of sensitive or harmful content.