ShallowJail: Steering Jailbreaks against Large Language Models

Large Language ModelsLLMs have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into producing harmful outputs. Existing jailbreaks are either...

PT-2021-21257 · Apache · Apache Ozone

Name of the Vulnerable Software and Affected Versions: Apache Ozone versions prior to 1.2.0 Description: The issue allows authenticated users with permission to the key to retrieve initially generated block tokens from the metadata database. These tokens can be used even after access has been...