Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

Authors: Javier Rando, Francesco Croce, Kryštof Mitka, Stepan Shabalin, Maksym Andriushchenko, Nicolas Flammarion, Florian Tramèr
Published: 2024-04-22 | Updated: 2024-06-06

Source: https://arxiv.org/abs/2404.14461

PDF: https://arxiv.org/pdf/2404.14461

AIにより推定されたラベル

プロンプトインジェクション バックドア攻撃 LLMセキュリティ

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.