Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation

• URL: http://arxiv.org/abs/2510.06605v1
• Date: Wed, 08 Oct 2025 03:27:38 GMT
• Title: Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
• Authors: Shuo Shao, Yiming Li, Hongwei Yao, Yifei Chen, Yuchen Yang, Zhan Qin,
• Abstract summary: Black-box methods often fail to generate distinctive Large Language Models fingerprints.<n>We propose ZeroPrint, a novel method that approximates information-rich gradients in a black-box setting using zeroth-order estimation.<n>Experiments on the standard benchmark show ZeroPrint achieves a state-of-the-art effectiveness and robustness, significantly outperforming existing black-box methods.
• Score: 33.83669045868836
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The substantial investment required to develop Large Language Models (LLMs) makes them valuable intellectual property, raising significant concerns about copyright protection. LLM fingerprinting has emerged as a key technique to address this, which aims to verify a model's origin by extracting an intrinsic, unique signature (a "fingerprint") and comparing it to that of a source model to identify illicit copies. However, existing black-box fingerprinting methods often fail to generate distinctive LLM fingerprints. This ineffectiveness arises because black-box methods typically rely on model outputs, which lose critical information about the model's unique parameters due to the usage of non-linear functions. To address this, we first leverage Fisher Information Theory to formally demonstrate that the gradient of the model's input is a more informative feature for fingerprinting than the output. Based on this insight, we propose ZeroPrint, a novel method that approximates these information-rich gradients in a black-box setting using zeroth-order estimation. ZeroPrint overcomes the challenge of applying this to discrete text by simulating input perturbations via semantic-preserving word substitutions. This operation allows ZeroPrint to estimate the model's Jacobian matrix as a unique fingerprint. Experiments on the standard benchmark show ZeroPrint achieves a state-of-the-art effectiveness and robustness, significantly outperforming existing black-box methods.

Related papers

• A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors [43.11304710234668]
  We introduce a novel fingerprinting framework that leverages the behavioral patterns induced by safety alignment.<n>In a large-scale identification task across 76 offspring models, our method achieves 100% accuracy in identifying the correct base model family.<n>We propose a theoretical framework to transform this private fingerprint into a publicly verifiable, privacy-preserving artifact.
  arXiv  Detail & Related papers  (2026-02-10T05:57:35Z)
• Lossless Copyright Protection via Intrinsic Model Fingerprinting [21.898748690761874]
  Existing protection methods modify the model to embed watermarks, which impairs performance.<n>We propose TrajPrint, a completely lossless and training-free framework that verifies model copyright by extracting unique manifold fingerprints.
  arXiv  Detail & Related papers  (2026-01-29T04:18:07Z)
• SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From [65.75182441010327]
  We propose a stronger and more intrinsic notion of LLM fingerprinting: SeedPrints.<n>We show that untrained models exhibit reproducible token selection biases conditioned solely on their parameters.<n> Experiments on LLaMA-style and Qwen-style models show that SeedPrints achieves seed-level distinguishability and can provide birth-to-lifecycle identity verification akin to a biometric fingerprint.
  arXiv  Detail & Related papers  (2025-09-30T15:34:08Z)
• Fingerprinting LLMs via Prompt Injection [16.907123772391213]
  Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization.<n>Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compare outputs across models using hand-crafted or random prompts, which are not robust to post-processing.<n>We propose LLMPrint, a novel detection framework that constructs fingerprints by exploiting LLMs' inherent vulnerability to prompt injection.
  arXiv  Detail & Related papers  (2025-09-29T19:54:36Z)
• SoK: Large Language Model Copyright Auditing via Fingerprinting [69.14570598973195]
  We introduce a unified framework and formal taxonomy that categorizes existing methods into white-box and black-box approaches.<n>We propose LeaFBench, the first systematic benchmark for evaluating LLM fingerprinting under realistic deployment scenarios.
  arXiv  Detail & Related papers  (2025-08-27T12:56:57Z)
• UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification [9.780530666330007]
  Fingerprinting large language models (LLMs) is essential for verifying model ownership, ensuring authenticity, and preventing misuse.<n>In this paper, we introduce a novel and efficient approach to fingerprinting LLMs by leveraging under-trained tokens.<n>Our method has minimal overhead and impact on model's performance, and does not require white-box access to target model's ownership identification.
  arXiv  Detail & Related papers  (2024-10-16T07:36:57Z)
• MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models [1.9249287163937978]
  We propose a novel fingerprinting method, MergePrint, to embed robust fingerprints capable of surviving model merging.<n> MergePrint enables black-box ownership verification, where owners only need to check if a model produces target outputs for specific fingerprint inputs.
  arXiv  Detail & Related papers  (2024-10-11T08:00:49Z)
• Instructional Fingerprinting of Large Language Models [57.72356846657551]
  We present a pilot study on fingerprinting Large language models (LLMs) as a form of very lightweight instruction tuning. Results on 11 popularly-used LLMs showed that this approach is lightweight and does not affect the normal behavior of the model. It also prevents publisher overclaim, maintains robustness against fingerprint guessing and parameter-efficient training, and supports multi-stage fingerprinting akin to MIT License.
  arXiv  Detail & Related papers  (2024-01-21T09:51:45Z)
• HuRef: HUman-REadable Fingerprint for Large Language Models [44.9820558213721]
  HuRef is a human-readable fingerprint for large language models.<n>It uniquely identifies the base model without interfering with training or exposing model parameters to the public.
  arXiv  Detail & Related papers  (2023-12-08T05:01:47Z)
• ProxyFAUG: Proximity-based Fingerprint Augmentation [81.15016852963676]
  ProxyFAUG is a rule-based, proximity-based method of fingerprint augmentation. The best performing positioning method on this dataset is improved by 40% in terms of median error and 6% in terms of mean error, with the use of the augmented dataset.
  arXiv  Detail & Related papers  (2021-02-04T15:59:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.