arXiv AI
Jul 29
Stemma: Induced Decision Regions Reveal LLM Provenance
arXiv:2607. 25880v1 Announce Type: cross Abstract: LLM provenance testing asks whether a suspect LLM belongs to the same lineage as a source.
RAFP: Identifying LLM Lineages via Rare-Region Fingerprints
arXiv:2505. 12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly released under restricted licenses, creating a growing need for robust model ownership verification.
Related stories
arXiv AI
Aug 11
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification
arXiv:2608. 08195v1 Announce Type: cross Abstract: Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment.
arXiv AI
Jul 31
FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing
arXiv:2508. 02092v3 Announce Type: replace-cross Abstract: Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable intellectual assets.
arXiv AI
Aug 11
Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
arXiv:2608. 07786v1 Announce Type: new Abstract: Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships that reflect model origin, ownership, and evolution.
arXiv Machine Learning
Jul 14
One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions
arXiv:2607. 10252v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights.
arXiv Machine Learning
1d ago
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
arXiv:2608. 14929v1 Announce Type: cross Abstract: Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented.
arXiv AI
Jun 3
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
arXiv:2606. 03330v1 Announce Type: cross Abstract: Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt, sampling configuration or quantization.
arXiv AI
Jul 29
Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models
arXiv:2607. 25633v1 Announce Type: cross Abstract: Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse.
arXiv AI
Aug 11
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States
arXiv:2608. 08024v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations.
arXiv AI
Jun 19
From Construction to Injection: Edit-Based Fingerprints for Large Language Models
arXiv:2509. 03122v4 Announce Type: replace-cross Abstract: Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misuse.
arXiv Machine Learning
Jun 2
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
arXiv:2606. 00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish.
arXiv AI
Jul 2
Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
arXiv:2407. 10887v4 Announce Type: replace-cross Abstract: Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to its original version and detect misuse.