Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916366438629376 |
|---|---|
| author | Zhao, Jiawei Chen, Kejiang Yuan, Xiaojian Zhang, Weiming |
| author_facet | Zhao, Jiawei Chen, Kejiang Yuan, Xiaojian Zhang, Weiming |
| contents | In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the generation of harmful content through meticulously crafted prompts. This vulnerability poses significant challenges to the secure use and promotion of LLMs. Existing defense methods offer protection from different perspectives but often suffer from insufficient effectiveness or a significant impact on the model's capabilities. In this paper, we propose a plug-and-play and easy-to-deploy jailbreak defense framework, namely Prefix Guidance (PG), which guides the model to identify harmful prompts by directly setting the first few tokens of the model's output. This approach combines the model's inherent security capabilities with an external classifier to defend against jailbreak attacks. We demonstrate the effectiveness of PG across three models and five attack methods. Compared to baselines, our approach is generally more effective on average. Additionally, results on the Just-Eval benchmark further confirm PG's superiority to preserve the model's performance. our code is available at https://github.com/weiyezhimeng/Prefix-Guidance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08924 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks Zhao, Jiawei Chen, Kejiang Yuan, Xiaojian Zhang, Weiming Cryptography and Security Artificial Intelligence Computation and Language In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the generation of harmful content through meticulously crafted prompts. This vulnerability poses significant challenges to the secure use and promotion of LLMs. Existing defense methods offer protection from different perspectives but often suffer from insufficient effectiveness or a significant impact on the model's capabilities. In this paper, we propose a plug-and-play and easy-to-deploy jailbreak defense framework, namely Prefix Guidance (PG), which guides the model to identify harmful prompts by directly setting the first few tokens of the model's output. This approach combines the model's inherent security capabilities with an external classifier to defend against jailbreak attacks. We demonstrate the effectiveness of PG across three models and five attack methods. Compared to baselines, our approach is generally more effective on average. Additionally, results on the Just-Eval benchmark further confirm PG's superiority to preserve the model's performance. our code is available at https://github.com/weiyezhimeng/Prefix-Guidance. |
| title | Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2408.08924 |