English
Related papers

Related papers: MoPe: Model Perturbation-based Privacy Attacks on …

200 papers

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

Machine Learning · Computer Science 2025-10-23 Xiaoyu Wu , Yifei Pang , Terrance Liu , Zhiwei Steven Wu

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

Model stealing, where a learner tries to recover an unknown model via carefully chosen queries, is a critical problem in machine learning, as it threatens the security of proprietary models and the privacy of data they are trained on. In…

Machine Learning · Computer Science 2024-11-13 Allen Liu , Ankur Moitra

The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…

Cryptography and Security · Computer Science 2026-02-12 Abhishek Saini , Haolin Jiang , Hang Liu

Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm has been especially…

Machine Learning · Computer Science 2024-10-18 John Abascal , Stanley Wu , Alina Oprea , Jonathan Ullman

Concerns about benchmark leakage in large language models for code (Code LLMs) have raised issues of data contamination and inflated evaluation metrics. The diversity and inaccessibility of many training datasets make it difficult to…

Software Engineering · Computer Science 2025-06-24 Hongzhou Rao , Yanjie Zhao , Wenjie Zhu , Ling Xiao , Meizhen Wang , Haoyu Wang

We reveal the theoretical foundations of techniques for editing large language models, and present new methods which can do so without requiring retraining. Our theoretical insights show that a single metric (a measure of the intrinsic…

Artificial Intelligence · Computer Science 2024-10-31 Oliver J. Sutton , Qinghua Zhou , Wei Wang , Desmond J. Higham , Alexander N. Gorban , Alexander Bastounis , Ivan Y. Tyukin

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

Cryptography and Security · Computer Science 2025-06-06 Lorenzo Rossi , Michael Aerni , Jie Zhang , Florian Tramèr

In psycholinguistic modeling, surprisal from larger pre-trained language models has been shown to be a poorer predictor of naturalistic human reading times. However, it has been speculated that this may be due to data leakage that caused…

Computation and Language · Computer Science 2025-06-03 Byung-Doh Oh , Hongao Zhu , William Schuler

Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…

Information Theory · Computer Science 2021-04-19 Sara Saeidian , Giulia Cervia , Tobias J. Oechtering , Mikael Skoglund

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Cryptography and Security · Computer Science 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Computation and Language · Computer Science 2024-10-31 Feng Yao , Yufan Zhuang , Zihao Sun , Sunan Xu , Animesh Kumar , Jingbo Shang

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…

Computation and Language · Computer Science 2025-10-21 Guillem Ramírez , Alexandra Birch , Ivan Titov

Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…

Machine Learning · Computer Science 2024-03-14 Guy Amit , Abigail Goldsteen , Ariel Farkash

Topic models provide a useful text-mining tool for learning, extracting, and discovering latent structures in large text corpora. Although a plethora of methods have been proposed for topic modeling, lacking in the literature is a formal…

Machine Learning · Statistics 2022-08-12 Yinyin Chen , Shishuang He , Yun Yang , Feng Liang

The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benchmarks even unintentionally. This problem subsequently makes…

Computation and Language · Computer Science 2025-09-19 Ruijie Hou , Yueyang Jiao , Hanxu Hu , Yingming Li , Wai Lam , Huajian Zhang , Hongyuan Lu

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Cryptography and Security · Computer Science 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi

Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…

Machine Learning · Computer Science 2023-03-08 Ganesh Del Grosso , Georg Pichler , Catuscia Palamidessi , Pablo Piantanida

Language models are generally trained on data spanning a wide range of topics (e.g., news, reviews, fiction), but they might be applied to an a priori unknown target distribution (e.g., restaurant reviews). In this paper, we first show that…

Computation and Language · Computer Science 2019-09-06 Yonatan Oren , Shiori Sagawa , Tatsunori B. Hashimoto , Percy Liang

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Machine Learning · Computer Science 2025-11-20 Bishnu Bhusal , Manoj Acharya , Ramneet Kaur , Colin Samplawski , Anirban Roy , Adam D. Cobb , Rohit Chadha , Susmit Jha