English
Related papers

Related papers: RoFL: Robust Fingerprinting of Language Models

200 papers

Protecting the intellectual property of large language models (LLMs) is crucial, given the substantial resources required for their training. Consequently, there is an urgent need for both model owners and third parties to determine whether…

Computation and Language · Computer Science 2026-02-17 Boyi Zeng , Lin Chen , Ziwei He , Xinbing Wang , Zhouhan Lin

As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of…

Machine Learning · Computer Science 2024-02-28 Aditya Desu , Xuanli He , Qiongkai Xu , Wei Lu

Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. Instead, it involves editing different upstream model…

Cryptography and Security · Computer Science 2024-11-05 Tianshuo Cong , Delong Ran , Zesen Liu , Xinlei He , Jinyuan Liu , Yichen Gong , Qi Li , Anyu Wang , Xiaoyun Wang

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

The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking…

Cryptography and Security · Computer Science 2026-04-16 Alexander Nemecek , Yuzhou Jiang , Erman Ayday

Recent studies on software tool manipulation with large language models (LLMs) mostly rely on closed model APIs. The industrial adoption of these models is substantially constrained due to the security and robustness risks in exposing…

Computation and Language · Computer Science 2023-05-29 Qiantong Xu , Fenglu Hong , Bo Li , Changran Hu , Zhengyu Chen , Jian Zhang

Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering operations such as fine-tuning (including PPO/DPO),…

Cryptography and Security · Computer Science 2026-04-08 Haobo Zhang , Zhenhua Xu , Junxian Li , Shangfeng Sheng , Dezhang Kong , Meng Han

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Machine Learning · Computer Science 2024-10-14 Yapei Chang , Kalpesh Krishna , Amir Houmansadr , John Wieting , Mohit Iyyer

Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data. While fine-tuning enhances performance by internalizing domain…

Multimodal LLMs (MLLMs) are capable of performing complex data analysis, visual question answering, generation, and reasoning tasks. However, their ability to analyze biometric data is relatively underexplored. In this work, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Ekta Gavas , Sudipta Banerjee , Chinmay Hegde , Nasir Memon

We present the first in depth study on the robustness of existing watermarking techniques applied to code generated by large language models (LLMs). As LLMs increasingly contribute to software development, watermarking has emerged as a…

Cryptography and Security · Computer Science 2025-08-21 Tarun Suresh , Shubham Ugare , Gagandeep Singh , Sasa Misailovic

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Cryptography and Security · Computer Science 2025-01-14 Kaiyi Pang , Tao Qi , Chuhan Wu , Minhao Bai , Minghu Jiang , Yongfeng Huang

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

Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked…

Cryptography and Security · Computer Science 2022-08-08 Thibault Maho , Teddy Furon , Erwan Le Merrer

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

Cryptography and Security · Computer Science 2025-11-17 Yanbo Dai , Zongjie Li , Zhenlan Ji , Shuai Wang

Large Language Models (LLMs) are often provided as a service via an API, making it challenging for developers to detect changes in their behavior. We present an approach to monitor LLMs for changes by comparing the distributions of…

Computation and Language · Computer Science 2025-04-18 Alden Dima , James Foulds , Shimei Pan , Philip Feldman

This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software development.…

Cryptography and Security · Computer Science 2025-02-11 Ruisi Zhang , Neusha Javidnia , Nojan Sheybani , Farinaz Koushanfar

Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs,…

Cryptography and Security · Computer Science 2024-12-09 Lingjie Chen , Ruizhong Qiu , Siyu Yuan , Zhining Liu , Tianxin Wei , Hyunsik Yoo , Zhichen Zeng , Deqing Yang , Hanghang Tong

A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification…

Computation and Language · Computer Science 2024-10-11 Tim R. Davidson , Viacheslav Surkov , Veniamin Veselovsky , Giuseppe Russo , Robert West , Caglar Gulcehre