Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.05047 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912123697758208 |
|---|---|
| author | Miceli-Barone, Antonio Valerio Sun, Zhifan |
| author_facet | Miceli-Barone, Antonio Valerio Sun, Zhifan |
| contents | LLM-based NLP systems typically work by embedding their input data into prompt templates which contain instructions and/or in-context examples, creating queries which are submitted to a LLM, and then parsing the LLM response in order to generate the system outputs. Prompt Injection Attacks (PIAs) are a type of subversion of these systems where a malicious user crafts special inputs which interfere with the prompt templates, causing the LLM to respond in ways unintended by the system designer.
Recently, Sun and Miceli-Barone proposed a class of PIAs against LLM-based machine translation. Specifically, the task is to translate questions from the TruthfulQA test suite, where an adversarial prompt is prepended to the questions, instructing the system to ignore the translation instruction and answer the questions instead.
In this test suite, we extend this approach to all the language pairs of the WMT 2024 General Machine Translation task. Moreover, we include additional attack formats in addition to the one originally studied. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05047 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A test suite of prompt injection attacks for LLM-based machine translation Miceli-Barone, Antonio Valerio Sun, Zhifan Computation and Language LLM-based NLP systems typically work by embedding their input data into prompt templates which contain instructions and/or in-context examples, creating queries which are submitted to a LLM, and then parsing the LLM response in order to generate the system outputs. Prompt Injection Attacks (PIAs) are a type of subversion of these systems where a malicious user crafts special inputs which interfere with the prompt templates, causing the LLM to respond in ways unintended by the system designer. Recently, Sun and Miceli-Barone proposed a class of PIAs against LLM-based machine translation. Specifically, the task is to translate questions from the TruthfulQA test suite, where an adversarial prompt is prepended to the questions, instructing the system to ignore the translation instruction and answer the questions instead. In this test suite, we extend this approach to all the language pairs of the WMT 2024 General Machine Translation task. Moreover, we include additional attack formats in addition to the one originally studied. |
| title | A test suite of prompt injection attacks for LLM-based machine translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.05047 |