Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

2026-05-27

AI Summary

This work addresses the absence of a unified identity mechanism for large language models (LLMs) across datasets, model weights, and generated content, which hinders ownership protection and provenance tracing. To bridge this gap, the paper introduces the concept of “implicit identity” and presents the first comprehensive identity abstraction framework spanning the entire LLM lifecycle. It systematically distinguishes between non-intrusive fingerprinting and intrusive digital watermarking, and establishes a taxonomy grounded in verification semantics—encompassing similarity attribution and key-based verification—and lifecycle stages. Through terminological standardization and multidimensional evaluation criteria—including identifiability, robustness, and deployability—the study provides a structured foundation for LLM identity technologies, thereby advancing reliable mechanisms for ownership assertion and content provenance.

Abstract

This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language models (LLMs) require substantial investments in data, computation, and expertise, and are increasingly deployed in high-stakes settings, making it critical to protect LLM-related assets and trace their origins. Existing work has rapidly expanded across dataset provenance, model ownership, and generated-content detection, but the field remains fragmented: fingerprinting and watermarking are often used inconsistently, and methods are typically studied within isolated asset-specific settings. To address this gap, we introduce implicit identity as a unifying abstraction for verifiable but not directly observable identity signals in LLM systems. We distinguish fingerprinting as non-intrusive identity derived from intrinsic characteristics, and watermarking as intrusive identity deliberately embedded into data, models, or generated content. We then propose a lifecycle-based taxonomy that organises techniques across datasets, models, and generated content, and further separates them by verification semantics: similarity-based attribution and keyed verification. Finally, we establish an evaluation framework centred on identifiability, robustness, and deployability, summarising representative metrics under realistic access and transformation regimes. By unifying terminology, lifecycle stages, and evaluation objectives, this survey provides a structured foundation for studying LLM identity technologies and for developing more reliable mechanisms for asset protection and provenance.

Problem

• LLM fingerprinting
• watermarking
• identity verification
• provenance
• ownership attribution

Innovation

• implicit identity
• fingerprinting
• watermarking
• LLM provenance
• lifecycle taxonomy