Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916605468868608 |
|---|---|
| author | Luo, Weidi Cao, He Liu, Zijing Wang, Yu Wong, Aidan Feng, Bing Yao, Yuan Li, Yu |
| author_facet | Luo, Weidi Cao, He Liu, Zijing Wang, Yu Wong, Aidan Feng, Bing Yao, Yuan Li, Yu |
| contents | With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly in domain-specific scenarios like chemistry, where a lack of specialized knowledge can lead to the generation of harmful responses to malicious queries. (ii) over-defensiveness, which compromises the general utility and responsiveness of LLMs. To mitigate these issues, we introduce a multi-agents-based defense framework, Guide for Defense (G4D), which leverages accurate external information to provide an unbiased summary of user intentions and analytically grounded safety response guidance. Extensive experiments on popular jailbreak attacks and benign datasets show that our G4D can enhance LLM's robustness against jailbreak attacks on general and domain-specific scenarios without compromising the model's general functionality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17922 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models Luo, Weidi Cao, He Liu, Zijing Wang, Yu Wong, Aidan Feng, Bing Yao, Yuan Li, Yu Artificial Intelligence With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly in domain-specific scenarios like chemistry, where a lack of specialized knowledge can lead to the generation of harmful responses to malicious queries. (ii) over-defensiveness, which compromises the general utility and responsiveness of LLMs. To mitigate these issues, we introduce a multi-agents-based defense framework, Guide for Defense (G4D), which leverages accurate external information to provide an unbiased summary of user intentions and analytically grounded safety response guidance. Extensive experiments on popular jailbreak attacks and benign datasets show that our G4D can enhance LLM's robustness against jailbreak attacks on general and domain-specific scenarios without compromising the model's general functionality. |
| title | Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2410.17922 |