# Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification

arXiv: https://arxiv.org/abs/2608.08195 · HTML: https://mlsanity.com/paper/2608.08195/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Builds on (most cited first, 30 of 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [2 OLMo 2 Furious](https://mlsanity.com/paper/2501.00656/) (2024)
- [Embedding Watermarks into Deep Neural Networks](https://mlsanity.com/paper/1701.04082/) (2017)
- [Stealing Part of a Production Language Model](https://mlsanity.com/paper/2403.06634/) (2024)
- [Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding](https://mlsanity.com/paper/2009.03015/) (2020)
- [Adversarial Frontier Stitching for Remote Neural Network Watermarking](https://mlsanity.com/paper/1711.01894/) (2017)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [Deep Neural Network Fingerprinting by Conferrable Adversarial Examples](https://mlsanity.com/paper/1912.00888/) (2019)
- [Watermark Stealing in Large Language Models](https://mlsanity.com/paper/2402.19361/) (2024)
- [On the Possibilities of AI-Generated Text Detection](https://mlsanity.com/paper/2304.04736/) (2023)
- [IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary](https://mlsanity.com/paper/1910.12903/) (2019)
- [Instructional Fingerprinting of Large Language Models](https://mlsanity.com/paper/2401.12255/) (2024)
- [Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations](https://mlsanity.com/paper/2202.08602/) (2022)
- [Watermarking Pre-trained Language Models with Backdooring](https://mlsanity.com/paper/2210.07543/) (2022)
- [Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models](https://mlsanity.com/paper/2112.05588/) (2021)
- [MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark](https://mlsanity.com/paper/2412.15194/) (2024)
- [TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification](https://mlsanity.com/paper/2402.12991/) (2024)
- [REEF: Representation Encoding Fingerprints for Large Language Models](https://mlsanity.com/paper/2410.14273/) (2024)
- [HuRef: HUman-REadable Fingerprint for Large Language Models](https://mlsanity.com/paper/2312.04828/) (2023)

## Built on by (most cited first, 1 of 1)

- [Forging LLM Authorship Fingerprints with Targeted Rewriting](https://mlsanity.com/paper/2609.38831/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment. Because deployed LLMs are commonly exposed only through query APIs, ownership verification must often rely on black-box text responses. This setting is difficult: generations are open-ended and can vary across repeated queries, while existing black-box fingerprints rely on signals that are fragile under a final-response interface, including full-text matching, soft behavioral features, or model-specific prompts designed not to transfer. We propose TCF (Targeted Counterfactual Fingerprinting), a black-box LLM fingerprinting framework that converts open-ended generation comparison into constrained-answer targeted counterfactual transfer. TCF restricts each verification query to a finite answer space, reducing the surface-form ambiguity that enters the verification score, and optimizes a prompt perturbation toward a counterfactual target different from the protected model's clean answer on the original prompt. Verification reduces to checking whether the suspect model's parsed final answer matches the recorded target. We introduce the source-model counterfactual margin (SCM), a protected-model-only quantity that certifies the target is unlikely before the perturbation and likely after it; SCM controls target selection, perturbation stopping, and fingerprint filtering. Under explicit derived-preservation and independent-transfer budgets motivated by local behavioral closeness, we derive a target-accuracy gap between derived and independent models. Across four LLM families, TCF achieves an average AUC of 0.9861, improving over TRAP, ProFLingo, and ZeroPrint by 0.07 to 0.19.