Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA)

Authors: Alan Aqrawi, Arian Abbasi
Published: 2024-09-04 | Updated: 2024-09-10

Source: https://arxiv.org/abs/2409.03131

PDF: https://arxiv.org/pdf/2409.03131

Labels Predicted by AI

コンテンツモデレーション 攻撃手法 LLMセキュリティ

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

This paper introduces a new method for adversarial attacks on large language models (LLMs) called the Single-Turn Crescendo Attack (STCA). Building on the multi-turn crescendo attack method introduced by Russinovich, Salem, and Eldan (2024), which gradually escalates the context to provoke harmful responses, the STCA achieves similar outcomes in a single interaction. By condensing the escalation into a single, well-crafted prompt, the STCA bypasses typical moderation filters that LLMs use to prevent inappropriate outputs. This technique reveals vulnerabilities in current LLMs and emphasizes the importance of stronger safeguards in responsible AI (RAI). The STCA offers a novel method that has not been previously explored.