Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
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_ | 1866929375862063104 |
|---|---|
| author | Rando, Javier Croce, Francesco Mitka, Kryštof Shabalin, Stepan Andriushchenko, Maksym Flammarion, Nicolas Tramèr, Florian |
| author_facet | Rando, Javier Croce, Francesco Mitka, Kryštof Shabalin, Stepan Andriushchenko, Maksym Flammarion, Nicolas Tramèr, Florian |
| contents | Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14461 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs Rando, Javier Croce, Francesco Mitka, Kryštof Shabalin, Stepan Andriushchenko, Maksym Flammarion, Nicolas Tramèr, Florian Computation and Language Artificial Intelligence Cryptography and Security Machine Learning Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research. |
| title | Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs |
| topic | Computation and Language Artificial Intelligence Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2404.14461 |