SOURCE-LINKED INTELLIGENCE

From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

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 cod

Read original source ↗ Open in workspace

recordType

paper

region

Global