Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.10360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916484114022400 |
|---|---|
| author | Zamir, Or |
| author_facet | Zamir, Or |
| contents | We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably impossible to distinguish between the responses of the original LLM and the LLM that hides a payload. In particular, the quality of generated text is not affected by the payload. Our approach extends a recent result of Christ, Gunn and Zamir (2023) who introduced an undetectable watermarking scheme for LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10360 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Excuse me, sir? Your language model is leaking (information) Zamir, Or Cryptography and Security Machine Learning We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably impossible to distinguish between the responses of the original LLM and the LLM that hides a payload. In particular, the quality of generated text is not affected by the payload. Our approach extends a recent result of Christ, Gunn and Zamir (2023) who introduced an undetectable watermarking scheme for LLMs. |
| title | Excuse me, sir? Your language model is leaking (information) |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2401.10360 |