Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims at Scale

13 February 2024

Papers citing "Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims at Scale"

1 / 1 papers shown

Title
Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation Aneta Zugecova Dominik Macko Ivan Srba Robert Moro Jakub Kopal Katarina Marcincinova Matus Mesarcik 67 0 0 18 Dec 2024