# ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models

arXiv: https://arxiv.org/abs/2601.08189 · HTML: https://mlsanity.com/paper/2601.08189/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 39 of its 55 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [Arcee's MergeKit: A Toolkit for Merging Large Language Models](https://mlsanity.com/paper/2403.13257/) (2024)
- [ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area](https://mlsanity.com/paper/2408.07246/) (2024)
- [Instructional Fingerprinting of Large Language Models](https://mlsanity.com/paper/2401.12255/) (2024)
- [CF-VLM:CounterFactual Vision-Language Fine-tuning](https://mlsanity.com/paper/2506.17267/) (2025)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models](https://mlsanity.com/paper/2112.05588/) (2021)
- [Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique](https://mlsanity.com/paper/2407.10887/) (2024)
- [REEF: Representation Encoding Fingerprints for Large Language Models](https://mlsanity.com/paper/2410.14273/) (2024)
- [MAT-Agent: Adaptive Multi-Agent Training Optimization](https://mlsanity.com/paper/2510.17845/) (2025)
- [HuRef: HUman-REadable Fingerprint for Large Language Models](https://mlsanity.com/paper/2312.04828/) (2023)
- [A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models](https://mlsanity.com/paper/2503.01854/) (2025)
- [A Fingerprint for Large Language Models](https://mlsanity.com/paper/2407.01235/) (2024)
- [Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends](https://mlsanity.com/paper/2508.11548/) (2025)
- [Hybrid Token Compression for Vision-Language Models](https://mlsanity.com/paper/2512.08240/) (2025)
- [Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging](https://mlsanity.com/paper/2404.05188/) (2024)
- [Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking](https://mlsanity.com/paper/2503.04636/) (2025)
- [UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification](https://mlsanity.com/paper/2410.12318/) (2024)

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

- [ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation](https://mlsanity.com/paper/2601.15330/) (2026)

## Abstract (arXiv)

Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce textscForgetMark, a stealthy fingerprinting framework that encodes provenance via targeted unlearning. It builds a compact, human-readable key--value set with an assistant model and predictive-entropy ranking, then trains lightweight LoRA adapters to suppress the original values on their keys while preserving general capabilities. Ownership is verified under black/gray-box access by aggregating likelihood and semantic evidence into a fingerprint success rate. By relying on probabilistic forgetting traces rather than fixed trigger--response patterns, textscForgetMark avoids high-perplexity triggers, reduces detectability, and lowers false triggers. Across diverse architectures and settings, it achieves 100% ownership verification on fingerprinted models while maintaining standard performance, surpasses backdoor baselines in stealthiness and robustness to model merging, and remains effective under moderate incremental fine-tuning. Our code and data are available at hrefhttps://github.com/Xuzhenhua55/ForgetMarkhttps://github.com/Xuzhenhua55/ForgetMark.