Abstract
Open-weight large language models (LLMs) can be copied, modified, and redeployed behind black-box APIs, making post-release ownership verification difficult. Existing black-box fingerprints often rely on secret query-key pairs that reproduce predefined responses, and can therefore be easily disrupted by fine-tuning, pruning, quantization, model merging, and serving-time prompt changes. We propose SimPrint, a recoverable semantic fingerprinting framework for black-box LLM ownership verification. Rather than relying on isolated exact matches, SimPrint encodes a private owner signature into a coded semantic fingerprint domain, distributing ownership evidence across natural binary question-answering probes. It implants only base-deviating probes through a low-interference batch update that preserves the original model behavior, and later recovers the signature by parsing suspect-model responses into reliable bits or erasures with an error-correcting recovery mechanism. Because verification only uses input-output queries, SimPrint remains applicable when model weights or activations are inaccessible. Experiments on three open-weight LLMs show that SimPrint reliably recovers the owner signature in both clean and modified settings, remains robust under fine-tuning, pruning, quantization, model merging, and serving-time perturbations, and maintains comparable downstream utility.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Hong, J., Peng, Y., Yu, H., Fang, H., Sun, S., & Chen, B. (2026). From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models. https://omanscience.com/en/articles/from-bits-to-beliefs-recoverable-semantic-fingerprints-for-black-box-verification-of-large-language-models
MLA 9
Hong, Jiaxin, et al. "From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models." https://omanscience.com/en/articles/from-bits-to-beliefs-recoverable-semantic-fingerprints-for-black-box-verification-of-large-language-models.
Chicago (author–date)
Hong, Jiaxin, Yuxin Peng, Hongyao Yu, Hao Fang, Shuoyang Sun, and Bin Chen. 2026. "From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models." https://omanscience.com/en/articles/from-bits-to-beliefs-recoverable-semantic-fingerprints-for-black-box-verification-of-large-language-models.
Harvard
Hong, J., Peng, Y., Yu, H., Fang, H., Sun, S. and Chen, B. (2026) 'From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models', Available at: https://omanscience.com/en/articles/from-bits-to-beliefs-recoverable-semantic-fingerprints-for-black-box-verification-of-large-language-models.
Vancouver
Hong J, Peng Y, Yu H, Fang H, Sun S, Chen B. From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models. https://omanscience.com/en/articles/from-bits-to-beliefs-recoverable-semantic-fingerprints-for-black-box-verification-of-large-language-models
IEEE
J. Hong, Y. Peng, H. Yu, H. Fang, S. Sun, and B. Chen, "From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models," https://omanscience.com/en/articles/from-bits-to-beliefs-recoverable-semantic-fingerprints-for-black-box-verification-of-large-language-models.