中文
相关论文

相关论文: Semantics-Preserved Distortion for Personal Privac…

200 篇论文

Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance…

计算与语言 · 计算机科学 2023-10-24 Lijie Hu , Ivan Habernal , Lei Shen , Di Wang

The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…

密码学与安全 · 计算机科学 2024-12-10 Guoshenghui Zhao , Eric Song

Besides its linguistic content, our speech is rich in biometric information that can be inferred by classifiers. Learning privacy-preserving representations for speech signals enables downstream tasks without sharing unnecessary, private…

声音 · 计算机科学 2021-06-18 Dimitrios Stoidis , Andrea Cavallaro

Distributed optimization and learning has recently garnered great attention due to its wide applications in sensor networks, smart grids, machine learning, and so forth. Despite rapid development, existing distributed optimization and…

机器学习 · 计算机科学 2024-03-04 Ziqin Chen , Yongqiang Wang

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full…

计算与语言 · 计算机科学 2025-08-29 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict and manipulate system actions. We argue that conventional information security measures can be ambiguous on the adversary's…

信息论 · 计算机科学 2017-05-09 Chi-Yo Tsai , Gaurav Kumar Agarwal , Christina Fragouli , Suhas Diggavi

As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods. One of the favorite privacy frameworks, differential privacy (DP), is perhaps the most compelling thanks to…

计算与语言 · 计算机科学 2025-08-14 Ivan Habernal

Data sharing enables critical advances in many research areas and business applications, but it may lead to inadvertent disclosure of sensitive summary statistics (e.g., means or quantiles). Existing literature only focuses on protecting a…

密码学与安全 · 计算机科学 2024-06-14 Shuaiqi Wang , Rongzhe Wei , Mohsen Ghassemi , Eleonora Kreacic , Vamsi K. Potluru

This paper proposes a novel privacy-preserving semantic segmentation method that can use independent keys for each client and image. In the proposed method, the model creator and each client encrypt images using locally generated keys, and…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Mare Hirose , Shoko Imaizumi , Hitoshi Kiya

Privacy preservation remains a key challenge in data mining and Natural Language Understanding (NLU). Previous research shows that the input text or even text embeddings can leak private information. This concern motivates our research on…

计算与语言 · 计算机科学 2021-08-23 Chen Qu , Weize Kong , Liu Yang , Mingyang Zhang , Michael Bendersky , Marc Najork

The emergence and evolution of Local Differential Privacy (LDP) and its various adaptations play a pivotal role in tackling privacy issues related to the vast amounts of data generated by intelligent devices, which are crucial for…

密码学与安全 · 计算机科学 2024-01-26 Likun Qin , Tianshuo Qiu

Ensuring the privacy of users whose data are used to train Natural Language Processing (NLP) models is necessary to build and maintain customer trust. Differential Privacy (DP) has emerged as the most successful method to protect the…

密码学与安全 · 计算机科学 2021-07-19 Ricardo Silva Carvalho , Theodore Vasiloudis , Oluwaseyi Feyisetan

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

密码学与安全 · 计算机科学 2021-02-03 Satyapriya Krishna , Rahul Gupta , Christophe Dupuy

Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for,…

计算与语言 · 计算机科学 2021-10-05 Mimansa Jaiswal , Emily Mower Provost

Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on perturbed text.…

计算与语言 · 计算机科学 2023-10-18 Stefan Arnold , Nils Kemmerzell , Annika Schreiner

Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather posit privacy at a group level, a setting we call integral…

机器学习 · 统计学 2019-07-04 Hisham Husain , Zac Cranko , Richard Nock

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…

机器学习 · 计算机科学 2011-02-18 Kamalika Chaudhuri , Claire Monteleoni , Anand D. Sarwate

Objective: To enable privacy-preserving learning of high quality generative and discriminative machine learning models from distributed electronic health records. Methods and Results: We describe general and scalable strategy to build…

密码学与安全 · 计算机科学 2018-06-19 Marina Blanton , Ah Reum Kang , Subhadeep Karan , Jaroslaw Zola

Deep neural networks have become a primary tool for solving problems in many fields. They are also used for addressing information retrieval problems and show strong performance in several tasks. Training these models requires large,…

信息检索 · 计算机科学 2017-07-25 Mostafa Dehghani , Hosein Azarbonyad , Jaap Kamps , Maarten de Rijke

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…

计算与语言 · 计算机科学 2022-12-19 C. M. Downey , Wei Dai , Huseyin A. Inan , Kim Laine , Saurabh Naik , Tomasz Religa