English
Related papers

Related papers: EditMF: Drawing an Invisible Fingerprint for Your …

200 papers

Fingerprinting Large Language Models (LLMs)is essential for provenance verification and model attribution. Existing fingerprinting methods are primarily evaluated after fine-tuning, where models have already acquired stable signatures from…

Cryptography and Security · Computer Science 2026-04-15 Yao Tong , Haonan Wang , Siquan Li , Kenji Kawaguchi , Tianyang Hu

The widespread deployment of large language models (LLMs) has intensified concerns around intellectual property (IP) protection, as model theft and unauthorized redistribution become increasingly feasible. To address this, model…

Computation and Language · Computer Science 2025-09-15 Zhenhua Xu , Xixiang Zhao , Xubin Yue , Shengwei Tian , Changting Lin , Meng Han

Fingerprinting refers to the process of identifying underlying Machine Learning (ML) models of AI Systemts, such as Large Language Models (LLMs), by analyzing their unique characteristics or patterns, much like a human fingerprint. The…

Machine Learning · Computer Science 2025-02-10 Devansh Bhardwaj , Naman Mishra

As content generated by Large Language Model (LLM) has grown exponentially, the ability to accurately identify and fingerprint such text has become increasingly crucial. In this work, we introduce a novel black-box approach for…

Cryptography and Security · Computer Science 2024-08-07 Dmitri Iourovitski , Sanat Sharma , Rakshak Talwar

Protecting the copyright of large language models (LLMs) has become crucial due to their resource-intensive training and accompanying carefully designed licenses. However, identifying the original base model of an LLM is challenging due to…

Computation and Language · Computer Science 2025-01-08 Boyi Zeng , Lizheng Wang , Yuncong Hu , Yi Xu , Chenghu Zhou , Xinbing Wang , Yu Yu , Zhouhan Lin

Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection…

Cryptography and Security · Computer Science 2026-05-20 Yuepeng Hu , Zhengyuan Jiang , Mengyuan Li , Osama Ahmed , Zhicong Huang , Cheng Hong , Neil Gong

Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple expert models into a single multi-task model, introduces a…

Cryptography and Security · Computer Science 2025-05-19 Shojiro Yamabe , Futa Waseda , Tsubasa Takahashi , Koki Wataoka

Growing concerns over the theft and misuse of Large Language Models (LLMs) have heightened the need for effective fingerprinting, which links a model to its original version to detect misuse. In this paper, we define five key properties for…

Cryptography and Security · Computer Science 2025-06-13 Mark Russinovich , Ahmed Salem

The protection of Intellectual Property (IP) for Large Language Models (LLMs) has become a critical concern as model theft and unauthorized commercialization escalate. While adversarial fingerprinting offers a promising black-box solution…

Cryptography and Security · Computer Science 2026-05-28 Zhebo Wang , Zhenhua Xu , Maike Li , Wenpeng Xing , Chunqiang Hu , Chen Zhi , Meng Han

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 \textsc{ForgetMark}, a…

Cryptography and Security · Computer Science 2026-01-21 Zhenhua Xu , Haobo Zhang , Zhebo Wang , Qichen Liu , Haitao Xu , Wenpeng Xing , Meng Han

The public accessibility of large vision-language models (LVLMs) raises serious concerns about unauthorized model reuse and intellectual property infringement. Existing ownership verification methods often rely on semantically abnormal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yifei Zhao , Qian Lou , Mengxin Zheng

Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence…

Cryptography and Security · Computer Science 2024-09-12 Heng Jin , Chaoyu Zhang , Shanghao Shi , Wenjing Lou , Y. Thomas Hou

The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs…

Cryptography and Security · Computer Science 2026-01-22 Zhenhua Xu , Yiran Zhao , Mengting Zhong , Dezhang Kong , Changting Lin , Tong Qiao , Meng Han

Simple fine-tuning can embed hidden text into large language models (LLMs), which is revealed only when triggered by a specific query. Applications include LLM fingerprinting, where a unique identifier is embedded to verify licensing…

Computation and Language · Computer Science 2025-06-27 Jakub Hoscilowicz , Pawel Popiolek , Jan Rudkowski , Jedrzej Bieniasz , Artur Janicki

Large Language Models (LLMs) are widely adopted, but their high training cost leads many developers to fine-tune existing open-source models. While most adhere to open-source licenses, some falsely claim original training despite clear…

Cryptography and Security · Computer Science 2025-12-09 Suqing Wang , Ziyang Ma , Li Xinyi , Zuchao Li

Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space…

Cryptography and Security · Computer Science 2025-09-03 Xubin Yue , Zhenhua Xu , Wenpeng Xing , Jiahui Yu , Mohan Li , Meng Han

The substantial investment required to develop Large Language Models (LLMs) makes them valuable intellectual property, raising significant concerns about copyright protection. LLM fingerprinting has emerged as a key technique to address…

Cryptography and Security · Computer Science 2026-01-22 Shuo Shao , Yiming Li , Hongwei Yao , Yifei Chen , Yuchen Yang , Zhan Qin

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Machine Learning · Computer Science 2026-03-03 Yiwei Chen , Soumyadeep Pal , Yimeng Zhang , Qing Qu , Sijia Liu

The ability to accurately identify authorship is crucial for verifying content authenticity and mitigating misinformation. Large Language Models (LLMs) have demonstrated an exceptional capacity for reasoning and problem-solving. However,…

Computation and Language · Computer Science 2024-10-23 Baixiang Huang , Canyu Chen , Kai Shu

Large Language Models (LLMs) have become increasingly prevalent across various sectors, raising critical concerns about model ownership and intellectual property protection. Although backdoor-based fingerprinting has emerged as a promising…

Cryptography and Security · Computer Science 2025-08-28 Jingxuan Zhang , Zhenhua Xu , Rui Hu , Wenpeng Xing , Xuhong Zhang , Meng Han