Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs

Understand

Large Language Models (LLMs) are increasingly being developed and applied, but their widespread use faces challenges.

• These include aligning LLMs' responses with human values to prevent harmful outputs, which is addressed through safety training methods.
• Even so, bad actors and malicious users have succeeded in attempts to manipulate the LLMs to generate misaligned responses for harmful questions such as methods to create a bomb in school labs, recipes for harmful drugs, and ways to evade privacy rights.
• Another challenge is the multilingual capabilities of LLMs, which enable the model to understand and respond in multiple languages.