RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process

October 11, 2024 Β· Declared Dead Β· πŸ› North American Chapter of the Association for Computational Linguistics

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Peiran Wang, Xiaogeng Liu, Chaowei Xiao arXiv ID 2410.08660 Category cs.CR: Cryptography & Security Cross-listed cs.AI Citations 9 Venue North American Chapter of the Association for Computational Linguistics Last Checked 4 months ago
Abstract
In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on ethical alignment, LLMs are still susceptible to jailbreak exploits. RePD operates on a one-shot learning model, wherein it accesses a database of pre-collected jailbreak prompt templates to identify and decompose harmful inquiries embedded within user prompts. This process involves integrating the decomposition of the jailbreak prompt into the user's original query into a one-shot learning example to effectively teach the LLM to discern and separate malicious components. Consequently, the LLM is equipped to first neutralize any potentially harmful elements before addressing the user's prompt in a manner that aligns with its ethical guidelines. RePD is versatile and compatible with a variety of open-source LLMs acting as agents. Through comprehensive experimentation with both harmful and benign prompts, we have demonstrated the efficacy of our proposed RePD in enhancing the resilience of LLMs against jailbreak attacks, without compromising their performance in responding to typical user requests.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Cryptography & Security

Died the same way β€” πŸ‘» Ghosted