Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
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_ | 1866911252352073728 |
|---|---|
| author | Sun, Chung-En Liu, Xiaodong Yang, Weiwei Weng, Tsui-Wei Cheng, Hao San, Aidan Galley, Michel Gao, Jianfeng |
| author_facet | Sun, Chung-En Liu, Xiaodong Yang, Weiwei Weng, Tsui-Wei Cheng, Hao San, Aidan Galley, Michel Gao, Jianfeng |
| contents | Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended responses. Current methods for generating these suffixes are computationally expensive and have low Attack Success Rates (ASR), especially against well-aligned models like Llama2 and Llama3. To overcome these limitations, we introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability. Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100\% ASR on various open-source LLMs. Moreover, it exhibits strong attack transferability to closed-source models, achieving 99\% ASR on GPT-3.5 and 49\% ASR on GPT-4, despite being optimized solely on Llama3. Beyond improving jailbreak ability, ADV-LLM provides valuable insights for future safety alignment research through its ability to generate large datasets for studying LLM safety. Our code is available at: https://github.com/SunChungEn/ADV-LLM |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18469 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities Sun, Chung-En Liu, Xiaodong Yang, Weiwei Weng, Tsui-Wei Cheng, Hao San, Aidan Galley, Michel Gao, Jianfeng Computation and Language Machine Learning Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended responses. Current methods for generating these suffixes are computationally expensive and have low Attack Success Rates (ASR), especially against well-aligned models like Llama2 and Llama3. To overcome these limitations, we introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability. Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100\% ASR on various open-source LLMs. Moreover, it exhibits strong attack transferability to closed-source models, achieving 99\% ASR on GPT-3.5 and 49\% ASR on GPT-4, despite being optimized solely on Llama3. Beyond improving jailbreak ability, ADV-LLM provides valuable insights for future safety alignment research through its ability to generate large datasets for studying LLM safety. Our code is available at: https://github.com/SunChungEn/ADV-LLM |
| title | Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2410.18469 |