Jailbreak prompts grouped into ten patterns and three categories successfully evade ChatGPT restrictions across 40 scenarios using 3,120 test questions.
Grounded theory in software engineering research: a critical review and guidelines,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2023 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
Jailbreak prompts grouped into ten patterns and three categories successfully evade ChatGPT restrictions across 40 scenarios using 3,120 test questions.