English
Related papers

Related papers: WaterDrum: Watermarking for Data-centric Unlearnin…

200 papers

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…

Machine Learning · Computer Science 2024-11-13 Kristian Georgiev , Roy Rinberg , Sung Min Park , Shivam Garg , Andrew Ilyas , Aleksander Madry , Seth Neel

Large language model (LLM)-based agents have recently gained considerable attention due to the powerful reasoning capabilities of LLMs. Existing research predominantly focuses on enhancing the task performance of these agents in diverse…

Multiagent Systems · Computer Science 2026-04-02 Dayong Ye , Tainqing Zhu , Congcong Zhu , Feng He , Qi He , Shang Wang , Bo Liu , Wanlei Zhou

The security of biomedical Multimodal Large Language Models (MLLMs) has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Dunyuan Xu , Xikai Yang , Yaoqian Li , Jinpeng Li , Pheng-Ann Heng

The development of large language models (LLMs) has raised concerns about potential misuse. One practical solution is to embed a watermark in the text, allowing ownership verification through watermark extraction. Existing methods primarily…

Cryptography and Security · Computer Science 2025-03-04 Yuhang Cai , Yaofei Wang , Donghui Hu , Chen Gu

The rapid progress of text-to-image diffusion models raises significant concerns regarding the unauthorized reproduction of trademarked content. While prior work targets general concepts (e.g., styles, celebrities), it fails to address…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Dawid Malarz , Filip Manjak , Maciej Zięba , Przemysław Spurek , Artur Kasymov

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

Machine Learning · Computer Science 2024-05-03 John Kirchenbauer , Jonas Geiping , Yuxin Wen , Jonathan Katz , Ian Miers , Tom Goldstein

Unlearning aims to remove copyrighted, sensitive, or private content from large language models (LLMs) without a full retraining. In this work, we develop a multi-task unlearning benchmark (LUME) which features three tasks: (1) unlearn…

Computation and Language · Computer Science 2025-02-28 Anil Ramakrishna , Yixin Wan , Xiaomeng Jin , Kai-Wei Chang , Zhiqi Bu , Bhanukiran Vinzamuri , Volkan Cevher , Mingyi Hong , Rahul Gupta

Watermarking the outputs of large language models (LLMs) is critical for provenance tracing, content regulation, and model accountability. Existing approaches often rely on access to model internals or are constrained by static rules and…

Machine Learning · Computer Science 2025-06-23 Agnibh Dasgupta , Abdullah Tanvir , Xin Zhong

With the passage of the Right to Be Forgotten (RTBF) regulations and the scaling up of language model training datasets, research on model unlearning in large language models (LLMs) has become more crucial. Before the era of LLMs, machine…

Computation and Language · Computer Science 2024-06-05 Bichen Wang , Yuzhe Zi , Yixin Sun , Yanyan Zhao , Bing Qin

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up…

Cryptography and Security · Computer Science 2026-02-09 Thibaud Gloaguen , Robin Staab , Nikola Jovanović , Martin Vechev

The rapid growth of Large Language Models (LLMs) has highlighted the pressing need for reliable mechanisms to verify content ownership and ensure traceability. Watermarking offers a promising path forward, but it remains limited by privacy…

Cryptography and Security · Computer Science 2026-01-21 Thomas Fargues , Ye Dong , Tianwei Zhang , Jin-Song Dong

There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses remain highly performance-oriented. In this paper, we switch…

Computation and Language · Computer Science 2025-10-29 Kyomin Hwang , Hyeonjin Kim , Seungyeon Kim , Sunghyun Wee , Nojun Kwak

The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…

Computation and Language · Computer Science 2024-06-11 Yepeng Liu , Yuheng Bu

Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards…

Computation and Language · Computer Science 2025-10-06 Jingqi Zhang , Ruibo Chen , Yingqing Yang , Peihua Mai , Heng Huang , Yan Pang

Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of watermarks that imprint a ``signal'' in LLM-generated text with…

Cryptography and Security · Computer Science 2025-05-15 Dor Tsur , Carol Xuan Long , Claudio Mayrink Verdun , Hsiang Hsu , Haim Permuter , Flavio P. Calmon

Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, several machine unlearning algorithms have been proposed to…

Computation and Language · Computer Science 2025-05-27 Keivan Rezaei , Khyathi Chandu , Soheil Feizi , Yejin Choi , Faeze Brahman , Abhilasha Ravichander

This paper introduces Unilogit, a novel self-distillation method for machine unlearning in Large Language Models. Unilogit addresses the challenge of selectively forgetting specific information while maintaining overall model utility, a…

Computation and Language · Computer Science 2025-05-12 Stefan Vasilev , Christian Herold , Baohao Liao , Seyyed Hadi Hashemi , Shahram Khadivi , Christof Monz

Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove…

Machine Learning · Computer Science 2024-11-01 Kairan Zhao , Meghdad Kurmanji , George-Octavian Bărbulescu , Eleni Triantafillou , Peter Triantafillou

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private…

Cryptography and Security · Computer Science 2024-12-18 Yuehan Zhang , Peizhuo Lv , Yinpeng Liu , Yongqiang Ma , Wei Lu , Xiaofeng Wang , Xiaozhong Liu , Jiawei Liu

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are…

Cryptography and Security · Computer Science 2025-06-13 Shayleen Reynolds , Hengzhi He , Dung Daniel T. Ngo , Saheed Obitayo , Niccolò Dalmasso , Guang Cheng , Vamsi K. Potluru , Manuela Veloso