English
Related papers

Related papers: Planting and Mitigating Memorized Content in Predi…

200 papers

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be…

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Chen Chen , Daochang Liu , Mubarak Shah , Chang Xu

Privacy preserving deep learning is an emerging field in machine learning that aims to mitigate the privacy risks in the use of deep neural networks. One such risk is training data extraction from language models that have been trained on…

Computation and Language · Computer Science 2024-12-02 Andor Diera , Nicolas Lell , Aygul Garifullina , Ansgar Scherp

Large Language models (LLMs) are trained on large amounts of data, which can include sensitive information that may compromise personal privacy. LLMs showed to memorize parts of the training data and emit those data verbatim when an…

Computation and Language · Computer Science 2023-05-03 Aly M. Kassem

Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust. Recent literature has demonstrated the applicability of a…

Machine Learning · Computer Science 2020-12-11 Oluwaseyi Feyisetan , Abhinav Aggarwal , Zekun Xu , Nathanael Teissier

Interactions with online Large Language Models raise privacy issues where providers can gather sensitive information about users and their companies from the prompts. While textual prompts can be sanitized using Differential Privacy, we…

Cryptography and Security · Computer Science 2025-06-16 Robin Carpentier , Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Dali Kaafar

We address the problem of how to "obfuscate" texts by removing stylistic clues which can identify authorship, whilst preserving (as much as possible) the content of the text. In this paper we combine ideas from "generalised differential…

Cryptography and Security · Computer Science 2019-02-06 Natasha Fernandes , Mark Dras , Annabelle McIver

Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization during…

Artificial Intelligence · Computer Science 2024-02-26 Shenglai Zeng , Yaxin Li , Jie Ren , Yiding Liu , Han Xu , Pengfei He , Yue Xing , Shuaiqiang Wang , Jiliang Tang , Dawei Yin

Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization…

Computation and Language · Computer Science 2021-06-03 Xiang Yue , Minxin Du , Tianhao Wang , Yaliang Li , Huan Sun , Sherman S. M. Chow

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Sunny Duan , Mikail Khona , Abhiram Iyer , Rylan Schaeffer , Ila R Fiete

Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When the noise is small in magnitude, these mechanisms are…

Computation and Language · Computer Science 2021-04-27 Zekun Xu , Abhinav Aggarwal , Oluwaseyi Feyisetan , Nathanael Teissier

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Daphne Ippolito , Matthew Jagielski , Katherine Lee , Florian Tramer , Chiyuan Zhang

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…

Computation and Language · Computer Science 2023-05-08 Davut Emre Tasar , Ceren Ocal Tasar

The field of privacy-preserving Natural Language Processing has risen in popularity, particularly at a time when concerns about privacy grow with the proliferation of Large Language Models. One solution consistently appearing in recent…

Computation and Language · Computer Science 2024-10-02 Stephen Meisenbacher , Florian Matthes

Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…

Computation and Language · Computer Science 2024-04-26 Zhihao Zhu , Ninglu Shao , Defu Lian , Chenwang Wu , Zheng Liu , Yi Yang , Enhong Chen

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

Machine Learning · Computer Science 2022-10-27 Justus Mattern , Zhijing Jin , Benjamin Weggenmann , Bernhard Schoelkopf , Mrinmaya Sachan

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

Machine Learning · Computer Science 2024-03-26 Xiao Li , Qiongxiu Li , Zhanhao Hu , Xiaolin Hu

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…

Cryptography and Security · Computer Science 2024-09-24 Nico Manzonelli , Wanrong Zhang , Salil Vadhan

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao