English
Related papers

Related papers: Knowledge Unlearning for Mitigating Privacy Risks …

200 papers

We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful…

Computation and Language · Computer Science 2024-02-20 Yuanshun Yao , Xiaojun Xu , Yang Liu

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…

Computation and Language · Computer Science 2025-09-09 Tomer Ashuach , Martin Tutek , Yonatan Belinkov

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep…

Machine Learning · Computer Science 2018-02-27 H. Brendan McMahan , Daniel Ramage , Kunal Talwar , Li Zhang

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform…

Cryptography and Security · Computer Science 2024-03-15 Biwei Yan , Kun Li , Minghui Xu , Yueyan Dong , Yue Zhang , Zhaochun Ren , Xiuzhen Cheng

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data…

Cryptography and Security · Computer Science 2021-09-15 Min Chen , Zhikun Zhang , Tianhao Wang , Michael Backes , Mathias Humbert , Yang Zhang

LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs as they integrate information from multiple…

Computation and Language · Computer Science 2025-05-06 Vaidehi Patil , Yi-Lin Sung , Peter Hase , Jie Peng , Tianlong Chen , Mohit Bansal

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

Large language models pretrained on a huge amount of data capture rich knowledge and information in the training data. The ability of data memorization and regurgitation in pretrained language models, revealed in previous studies, brings…

Cryptography and Security · Computer Science 2023-12-06 Xinwei Wu , Junzhuo Li , Minghui Xu , Weilong Dong , Shuangzhi Wu , Chao Bian , Deyi Xiong

As the deployment of pre-trained language models (PLMs) expands, pressing security concerns have arisen regarding the potential for malicious extraction of training data, posing a threat to data privacy. This study is the first to provide a…

Computation and Language · Computer Science 2023-05-26 Shotaro Ishihara

Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with…

Computation and Language · Computer Science 2022-10-21 Jie Huang , Hanyin Shao , Kevin Chen-Chuan Chang

Large Language Models (LLMs) trained on extensive datasets often learn sensitive information, which raises significant social and legal concerns under principles such as the "Right to be forgotten." Retraining entire models from scratch to…

Computation and Language · Computer Science 2025-04-18 Kun-Woo Kim , Ji-Hoon Park , Ju-Min Han , Seong-Whan Lee

Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory element identification, and cross-task transfer learning. However, as these…

Machine Learning · Computer Science 2026-03-11 Alexander Nemecek , Wenbiao Li , Xiaoqian Jiang , Jaideep Vaidya , Erman Ayday

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…

Computation and Language · Computer Science 2025-08-14 Ying Yin , Ivan Habernal

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

Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…

Computation and Language · Computer Science 2022-06-27 Xuandong Zhao , Lei Li , Yu-Xiang Wang

Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have increased drastically. This raises the key question of…

Artificial Intelligence · Computer Science 2024-05-07 Robin Staab , Mark Vero , Mislav Balunović , Martin Vechev

Federated Learning (FL) offers a promising paradigm for training Large Language Models (LLMs) in a decentralized manner while preserving data privacy and minimizing communication overhead. This survey examines recent advancements in…

Machine Learning · Computer Science 2025-05-12 Youyang Qu , Ming Liu , Tianqing Zhu , Longxiang Gao , Shui Yu , Wanlei Zhou

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Computation and Language · Computer Science 2022-12-19 C. M. Downey , Wei Dai , Huseyin A. Inan , Kim Laine , Saurabh Naik , Tomasz Religa

Machine unlearning is an emerging technique that removes the influence of a subset of training data (forget set) from a model without full retraining, with applications including privacy protection, content moderation, and model correction.…

Computation and Language · Computer Science 2025-10-02 Hong kyu Lee , Ruixuan Liu , Li Xiong
‹ Prev 1 3 4 5 6 7 10 Next ›