EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint

• URL: http://arxiv.org/abs/2509.03058v1
• Date: Wed, 03 Sep 2025 06:40:57 GMT
• Title: EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint
• Authors: Zhenhua Xu, Meng Han, Wenpeng Xing,
• Abstract summary: We propose EverTracer, a novel gray-box fingerprinting framework that ensures stealthy and robust model provenance tracing.<n>EverTracer is the first to repurpose Membership Inference Attacks (MIAs) for defensive use.<n>It consists of Fingerprint Injection, which fine-tunes the model on any natural language data without detectable artifacts, and Verification, which leverages calibrated probability variation signal to distinguish fingerprinted models.
• Score: 22.154946163092117
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The proliferation of large language models (LLMs) has intensified concerns over model theft and license violations, necessitating robust and stealthy ownership verification. Existing fingerprinting methods either require impractical white-box access or introduce detectable statistical anomalies. We propose EverTracer, a novel gray-box fingerprinting framework that ensures stealthy and robust model provenance tracing. EverTracer is the first to repurpose Membership Inference Attacks (MIAs) for defensive use, embedding ownership signals via memorization instead of artificial trigger-output overfitting. It consists of Fingerprint Injection, which fine-tunes the model on any natural language data without detectable artifacts, and Verification, which leverages calibrated probability variation signal to distinguish fingerprinted models. This approach remains robust against adaptive adversaries, including input level modification, and model-level modifications. Extensive experiments across architectures demonstrate EverTracer's state-of-the-art effectiveness, stealthness, and resilience, establishing it as a practical solution for securing LLM intellectual property. Our code and data are publicly available at https://github.com/Xuzhenhua55/EverTracer.

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)
• ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models [21.330293192156596]
  textscForgetMark is a stealthy fingerprinting framework that encodes provenance via targeted unlearning.<n>It builds a compact, human-readable key--value set with an assistant model and predictive-entropy ranking, then trains lightweight LoRA adapters to suppress the original values on their keys while preserving general capabilities.
  arXiv  Detail & Related papers  (2026-01-13T03:41:28Z)
• 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)
• CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor [21.71721725818432]
  We introduce CTCC, a novel rule-driven fingerprinting framework.<n>CTCC encodes contextual correlations across multiple dialogue turns, such as counterfactual, rather than relying on token-level or single-turn triggers.<n>Our findings position CTCC as a reliable and practical solution for ownership verification in real-world LLM deployment scenarios.
  arXiv  Detail & Related papers  (2025-09-05T05:59:50Z)
• Deep Learning Models for Robust Facial Liveness Detection [56.08694048252482]
  This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques.<n>By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision.
  arXiv  Detail & Related papers  (2025-08-12T17:19:20Z)
• FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint [22.398234847594242]
  Model fingerprinting is a widely adopted approach to safeguard the intellectual property rights of open-source models.<n>In this paper, we reveal that they are vulnerable to false claim attacks where adversaries falsely assert ownership of any third-party model.<n>Motivated by these findings, we propose a targeted fingerprinting paradigm (i.e., FIT-Print) to counteract false claim attacks.
  arXiv  Detail & Related papers  (2025-01-26T13:00:58Z)
• Exploring Federated Learning Dynamics for Black-and-White-Box DNN Traitor Tracing [49.1574468325115]
  This paper explores the adaptation of black-and-white traitor tracing watermarking to Federated Learning. Results show that collusion-resistant traitor tracing, identifying all data-owners involved in a suspected leak, is feasible in an FL framework, even in early stages of training.
  arXiv  Detail & Related papers  (2024-07-02T09:54:35Z)
• On the Robustness of Dataset Inference [21.321310557323383]
  Machine learning (ML) models are costly to train as they can require a significant amount of data, computational resources and technical expertise. Ownership verification techniques allow the victims of model stealing attacks to demonstrate that a suspect model was in fact stolen from theirs. A fingerprinting technique, dataset inference (DI), has been shown to offer better robustness and efficiency than prior methods.
  arXiv  Detail & Related papers  (2022-10-24T22:17:55Z)
• MOVE: Effective and Harmless Ownership Verification via Embedded External Features [104.97541464349581]
  We propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously.<n>We conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features.<n>We then train a meta-classifier to determine whether a model is stolen from the victim.
  arXiv  Detail & Related papers  (2022-08-04T02:22:29Z)
• Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations [22.89321897726347]
  We propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model. Our framework can detect model IP breaches with confidence 99.99 %$ within only $20$ fingerprints of the suspect model.
  arXiv  Detail & Related papers  (2022-02-17T11:29:50Z)
• Defending against Model Stealing via Verifying Embedded External Features [90.29429679125508]
  adversaries can steal' deployed models even when they have no training samples and can not get access to the model parameters or structures. We explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified emphexternal features. Our method is effective in detecting different types of model stealing simultaneously, even if the stolen model is obtained via a multi-stage stealing process.
  arXiv  Detail & Related papers  (2021-12-07T03:51:54Z)
• Fingerprinting Image-to-Image Generative Adversarial Networks [53.02510603622128]
  Generative Adversarial Networks (GANs) have been widely used in various application scenarios. This paper presents a novel fingerprinting scheme for the Intellectual Property protection of image-to-image GANs based on a trusted third party.
  arXiv  Detail & Related papers  (2021-06-19T06:25:10Z)
• Responsible Disclosure of Generative Models Using Scalable Fingerprinting [70.81987741132451]
  Deep generative models have achieved a qualitatively new level of performance. There are concerns on how this technology can be misused to spoof sensors, generate deep fakes, and enable misinformation at scale. Our work enables a responsible disclosure of such state-of-the-art generative models, that allows researchers and companies to fingerprint their models.
  arXiv  Detail & Related papers  (2020-12-16T03:51:54Z)

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.