Newest papers

Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models

Yanan He, Yanli Chen, Ling Xiong, Gejian Zhao, Hanzhou Wu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30626 · cited by 0 works (OpenAlex) · open-access PDF

Korean

대형 언어 모델 (LLMs)의 점진적 인 인증 및 재사용은 개방형 체크포인트로서 모델 지문을 소유권 보호 및 오프라인 감사에 중요하게 만듭니다. 기존의 분리 지문 방법은 일반적으로 쿼리 응답, 생성된 출력 또는 입력 유도 된 활성화에서 증거를 구축합니다. 개방형 설정에서 효과적이지만, 모델 지문은 인증 선택, 디코딩 구성, 추론 환경 및 전달 구현에 영향을 미칠 수 있습니다. 여기에서 우리는 LLN (FFNs)에서 그들의 적용성을 제한 할 수 있습니다. 구체적으로, 프레임 워크는 GATE의 단일 값 분산에서 GATE 증거 스칼러 기능을 구축합니다. 이 프레임 워크는 g feed-forward 네트워크 (FFN

Machine translation (Meta M2M100); the English original follows.

Abstract

The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting important for ownership protection and offline auditing. Existing fingerprinting methods typically construct evidence from query responses, generated outputs, or input-induced activations. Although effective in representation-based settings, they can be affected by prompt selection, decoding configuration, inference environment, and forward-pass implementation, which may limit their applicability. Here we introduce a model-intrinsic weight-level framework that derives compact fingerprints from spectral structures encoded in LLM parameters. Specifically, the framework constructs GATE spectral scalar features from the singular-value distributions of GATE projection weights in gated feed-forward networks (FFNs), and aggregates the resulting layer-wise features through depth-wise segmented pooling to form a model-level fingerprint. Such representation preserves coarse layer-depth organization while reducing dependence on strict layer-to-layer alignment, enabling comparison across LLMs with different depths. The similarity between fingerprints is computed by linear centered kernel alignment. The entire pipeline is training-free and does not require input samples, generated outputs, forward activations, or an auxiliary verifier. Experiments on representative LLM families and post-training variants have demonstrated a clear separation between source-related models and unrelated ones, and stable similarity under instruction tuning, quantization, pruning, and distillation-related modifications, which verify that spectral features are robust evidence for LLM fingerprinting.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Decoding methods, Pipeline (software), Inference, Pooling, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange