English
Related papers

Related papers: Concept-Aware Privacy Mechanisms for Defending Emb…

200 papers

We present SPARSI, a theoretical framework for partitioning sensitive data across multiple non-colluding adversaries. Most work in privacy-aware data sharing has considered disclosing summaries where the aggregate information about the data…

Databases · Computer Science 2013-03-12 Theodoros Rekatsinas , Amol Deshpande , Ashwin Machanavajjhala

In decentralized networks, nodes cannot ensure that their shared information will be securely preserved by their neighbors, making privacy vulnerable to inference by curious nodes. Adding calibrated random noise before communication to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-13 Yiming Zhou , Kaiping Xue , Enhong Chen

Quantum computing revolutionizes the way of solving complex problems and handling vast datasets, which shows great potential to accelerate the machine learning process. However, data leakage in quantum machine learning (QML) may present…

Quantum Physics · Physics 2024-03-08 Keyi Ju , Xiaoqi Qin , Hui Zhong , Xinyue Zhang , Miao Pan , Baoling Liu

Federated Learning (FL) enables collaborative model training without direct data sharing, yet it remains vulnerable to privacy attacks such as model inversion and membership inference. Existing differential privacy (DP) solutions for FL…

Cryptography and Security · Computer Science 2026-01-06 Yunbo Li , Jiaping Gui , Fanchao Meng , Yue Wu

We propose a new computationally efficient privacy-preserving identification framework based on layered sparse coding. The key idea of the proposed framework is a sparsifying transform learning with ambiguization, which consists of a…

Information Theory · Computer Science 2018-06-25 Behrooz Razeghi , Slava Voloshynovskiy , Sohrab Ferdowsi , Dimche Kostadinov

Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the formal guarantees of differential privacy (DP) in the embedding…

Computation and Language · Computer Science 2024-10-11 Tianhao Huang , Tao Yang , Ivan Habernal , Lijie Hu , Di Wang

In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at…

Machine Learning · Statistics 2021-10-28 Tejas Kulkarni , Joonas Jälkö , Samuel Kaski , Antti Honkela

The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a…

Computation and Language · Computer Science 2024-05-06 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Machine Learning · Computer Science 2021-08-17 Xue Yang , Yan Feng , Weijun Fang , Jun Shao , Xiaohu Tang , Shu-Tao Xia , Rongxing Lu

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…

Machine Learning · Computer Science 2026-01-19 Lele Zheng , Xiang Wang , Tao Zhang , Yang Cao , Ke Cheng , Yulong Shen

We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…

Cryptography and Security · Computer Science 2021-03-29 Arnaud Grivet Sébert , Rafael Pinot , Martin Zuber , Cédric Gouy-Pailler , Renaud Sirdey

Federated Learning, as a popular paradigm for collaborative training, is vulnerable against privacy attacks. Different privacy levels regarding users' attitudes need to be satisfied locally, while a strict privacy guarantee for the global…

Cryptography and Security · Computer Science 2023-05-29 Yixuan Liu , Suyun Zhao , Li Xiong , Yuhan Liu , Hong Chen

Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern. An effective solution to this problem is to train models with differential privacy, which provides rigorous…

Machine Learning · Computer Science 2024-07-04 Ergute Bao , Yizheng Zhu , Xiaokui Xiao , Yin Yang , Beng Chin Ooi , Benjamin Hong Meng Tan , Khin Mi Mi Aung

NLP models trained with differential privacy (DP) usually adopt the DP-SGD framework, and privacy guarantees are often reported in terms of the privacy budget $\epsilon$. However, $\epsilon$ does not have any intrinsic meaning, and it is…

Machine Learning · Computer Science 2025-03-19 Pedro Faustini , Natasha Fernandes , Annabelle McIver , Mark Dras

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even…

Cryptography and Security · Computer Science 2022-03-15 Dayong Ye , Sheng Shen , Tianqing Zhu , Bo Liu , Wanlei Zhou

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

Cryptography and Security · Computer Science 2025-11-18 Hasini Jayathilaka

Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a vari-ety…

Computation and Language · Computer Science 2017-09-25 Arpita Roy , Youngja Park , SHimei Pan

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel…

Machine Learning · Computer Science 2020-10-06 Lingjuan Lyu , Xuanli He , Yitong Li

The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of…

Computation and Language · Computer Science 2024-04-05 Stephen Meisenbacher , Nihildev Nandakumar , Alexandra Klymenko , Florian Matthes

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson