ML Security PapersFrom Construction to Injection: Edit-Based Fingerprints for Large Language Models
Yue Li, Xin Yi, Dongsheng Shi et al. · East China Normal University · Hasso Plattner Institute
Embeds ownership fingerprints into LLM weights via knowledge editing to detect unauthorized redistribution post-modification
Establishing reliable and verifiable fingerprinting mechanisms is fundamental to controlling the unauthorized redistribution of large language models (LLMs). However, existing approaches face two major challenges: (a) ensuring imperceptibility, including resistance to statistical identification and avoidance of accidental activation during fingerprint construction, and (b) preserving both model utility and fingerprint detectability under subsequent model modifications. To address these challenges, we propose an end-to-end fingerprinting framework with two components. First, we design a rule-based code-mixing fingerprint (CF) that maps natural-query-like prompts to multi-candidate targets, reducing accidental triggering via high-complexity code-mixing formulations. Second, we introduce Multi-Candidate Editing (MCEdit), which jointly optimizes multi-candidate targets and enforces margins between target and non-target outputs to improve post-modification detectability. Extensive experiments demonstrate that our framework provides a robust and practical solution for fingerprinting LLMs.