FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing
Published in arXiv preprint, 2025
Recommended citation: Wang, S., Liu, C., Wang, Y., & Xu, L. (2025). "FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing." arXiv preprint arXiv:2508.02092. https://arxiv.org/pdf/2508.02092
Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable intellectual assets. Nevertheless, these AI assets remain vulnerable to unauthorized redistribution and commercial exploitation through fine-tuning or black-box deployment. Current fingerprinting approaches face a fundamental trade-off: intrinsic methods require full parameter access, while backdoor-based techniques employ statistically anomalous triggers easily detected and filtered by adversaries.
To address these limitations, we introduce FPEdit, a novel framework that leverages knowledge editing to inject semantically coherent natural language fingerprints through sparse, targeted modifications to model weights. Our approach introduces Promote-Suppress Value Vector Optimization, which simultaneously enhances target token likelihood while suppressing competing tokens, ensuring robust fingerprint integration without degrading core model functionality.
Key Results:
- Achieves 95–100% fingerprint retention under both full-parameter fine-tuning and parameter-efficient adaptation
- Remains robust under quantization, pruning, and stochastic decoding
- Embeds 10 fingerprint pairs into LLaMA2-7B in under 2 minutes using less than 30 GB GPU memory