Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned 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_ | 1866911963890581504 |
|---|---|
| author | Liu, Xiao Li, Liangzhi Xiang, Tong Ye, Fuying Wei, Lu Li, Wangyue Garcia, Noa |
| author_facet | Liu, Xiao Li, Liangzhi Xiang, Tong Ye, Fuying Wei, Lu Li, Wangyue Garcia, Noa |
| contents | With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse, a risk remains, particularly when models encounter adversarial inputs. This study unveils an attack mechanism that capitalizes on human conversation strategies to extract harmful information from LLMs. We delineate three pivotal strategies: (i) decomposing malicious questions into seemingly innocent sub-questions; (ii) rewriting overtly malicious questions into more covert, benign-sounding ones; (iii) enhancing the harmfulness of responses by prompting models for illustrative examples. Unlike conventional methods that target explicit malicious responses, our approach delves deeper into the nature of the information provided in responses. Through our experiments conducted on GPT-3.5-turbo, GPT-4, and Llama2, our method has demonstrated a marked efficacy compared to conventional attack methods. In summary, this work introduces a novel attack method that outperforms previous approaches, raising an important question: How to discern whether the ultimate intent in a dialogue is malicious? |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15399 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models Liu, Xiao Li, Liangzhi Xiang, Tong Ye, Fuying Wei, Lu Li, Wangyue Garcia, Noa Computation and Language Artificial Intelligence Cryptography and Security With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse, a risk remains, particularly when models encounter adversarial inputs. This study unveils an attack mechanism that capitalizes on human conversation strategies to extract harmful information from LLMs. We delineate three pivotal strategies: (i) decomposing malicious questions into seemingly innocent sub-questions; (ii) rewriting overtly malicious questions into more covert, benign-sounding ones; (iii) enhancing the harmfulness of responses by prompting models for illustrative examples. Unlike conventional methods that target explicit malicious responses, our approach delves deeper into the nature of the information provided in responses. Through our experiments conducted on GPT-3.5-turbo, GPT-4, and Llama2, our method has demonstrated a marked efficacy compared to conventional attack methods. In summary, this work introduces a novel attack method that outperforms previous approaches, raising an important question: How to discern whether the ultimate intent in a dialogue is malicious? |
| title | Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2407.15399 |