all InfoSec news
Instructional Fingerprinting of Large Language Models. (arXiv:2401.12255v1 [cs.CR] CROSS LISTED)
cs.CR updates on arXiv.org arxiv.org
The exorbitant cost of training Large language models (LLMs) from scratch
makes it essential to fingerprint the models to protect intellectual property
via ownership authentication and to ensure downstream users and developers
comply with their license terms (e.g. restricting commercial use). In this
study, we present a pilot study on LLM fingerprinting as a form of very
lightweight instruction tuning. Model publisher specifies a confidential
private key and implants it as an instruction backdoor that causes the LLM to
generate …
arxiv authentication commercial cost developers fingerprint fingerprinting intellectual property language language models large license llms ownership pilot property protect study terms training