English
Related papers

Related papers: DEEProtect: Enabling Inference-based Access Contro…

200 papers

Many modern statistical analysis and machine learning applications require training models on sensitive user data. Under a formal definition of privacy protection, differentially private algorithms inject calibrated noise into the…

Machine Learning · Statistics 2025-04-01 Yifei Xiong , Nianqiao Phyllis Ju , Sanguo Zhang

Security monitoring via ubiquitous cameras and their more extended in intelligent buildings stand to gain from advances in signal processing and machine learning. While these innovative and ground-breaking applications can be considered as…

Cryptography and Security · Computer Science 2026-05-06 Mehmet Yamac , Mete Ahishali , Nikolaos Passalis , Jenni Raitoharju , Bulent Sankur , Moncef Gabbouj

Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text…

Machine Learning · Computer Science 2019-10-22 Oluwaseyi Feyisetan , Borja Balle , Thomas Drake , Tom Diethe

Today's mobile devices sense, collect, and store huge amounts of personal information, which users share with family and friends through a wide range of applications. Once users give applications access to their data, they must implicitly…

The financial sector's adoption of technology-driven data analysis has enhanced operational efficiency and revenue generation by leveraging personal sensitive data. However, the inherent characteristics of blockchain hinder decentralized…

Cryptography and Security · Computer Science 2023-11-13 Zhuangtong Huang , Jiawei Zhu , Zhongyu Huang , Yixin Xu , Jerome Yen , Ye Wang

Current smartphone operating systems regulate application permissions by prompting users on an ask-on-first-use basis. Prior research has shown that this method is ineffective because it fails to account for context: the circumstances under…

Cryptography and Security · Computer Science 2017-03-08 Primal Wijesekera , Arjun Baokar , Lynn Tsai , Joel Reardon , Serge Egelman , David Wagner , Konstantin Beznosov

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…

Machine Learning · Statistics 2019-07-04 Hisham Husain , Zac Cranko , Richard Nock

A typical setup in many machine learning scenarios involves a server that holds a model and a user that possesses data, and the challenge is to perform inference while safeguarding the privacy of both parties. Private Inference has been…

Information Theory · Computer Science 2023-11-27 Zirui Deng , Vinayak Ramkumar , Rawad Bitar , Netanel Raviv

To protect user privacy in data analysis, a state-of-the-art strategy is differential privacy in which scientific noise is injected into the real analysis output. The noise masks individual's sensitive information contained in the dataset.…

Cryptography and Security · Computer Science 2018-06-20 Xuan-Son Vu , Lili Jiang

Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for sensing and computer vision. This approach typically involves a three-stage…

Cryptography and Security · Computer Science 2024-10-29 Mohamed Seif , Yuqi Nie , Andrea J. Goldsmith , H. Vincent Poor

Authentication of smartphone users is important because a lot of sensitive data is stored in the smartphone and the smartphone is also used to access various cloud data and services. However, smartphones are easily stolen or co-opted by an…

Cryptography and Security · Computer Science 2017-09-01 Wei-Han Lee , Ruby B. Lee

Mobile Graphical User Interface (GUI) agents have demonstrated strong capabilities in automating complex smartphone tasks by leveraging multimodal large language models (MLLMs) and system-level control interfaces. However, this paradigm…

Cryptography and Security · Computer Science 2026-04-28 Lepeng Zhao , Zhenhua Zou , Shuo Li , Zhuotao Liu

Third-party applications have become an essential part of today's online ecosystem, enhancing the functionality of popular platforms. However, the intensive data exchange underlying their proliferation has increased concerns about…

Cryptography and Security · Computer Science 2024-05-03 Shuaishuai Liu , Gergely Biczók

Internet of Things devices are envisioned to penetrate essentially all aspects of life, including homes and urbanspaces, in use cases such as health care, assisted living, and smart cities. One often proposed solution for dealing with the…

Software Engineering · Computer Science 2020-03-17 Martin Henze , Lars Hermerschmidt , Daniel Kerpen , Roger Häußling , Bernhard Rumpe , Klaus Wehrle

Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research has shown that…

Cryptography and Security · Computer Science 2023-06-16 Lin Duan , Jingwei Sun , Yiran Chen , Maria Gorlatova

Participatory sensing is emerging as an innovative computing paradigm that targets the ubiquity of always-connected mobile phones and their sensing capabilities. In this context, a multitude of pioneering applications increasingly carry out…

Cryptography and Security · Computer Science 2013-08-14 Emiliano De Cristofaro , Claudio Soriente

Collaborative inference has recently emerged as an attractive framework for applying deep learning to Internet of Things (IoT) applications by splitting a DNN model into several subpart models among resource-constrained IoT devices and the…

Cryptography and Security · Computer Science 2022-11-22 Jihyeon Ryu , Yifeng Zheng , Yansong Gao , Sharif Abuadbba , Junyaup Kim , Dongho Won , Surya Nepal , Hyoungshick Kim , Cong Wang

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…

Internet of Things is growing rapidly, with many connected devices now available to consumers. With this growth, the IoT apps that manage the devices from smartphones raise significant security concerns. Typically, these apps are secured…

Cryptography and Security · Computer Science 2018-11-06 Davino Mauro Junior , Kiev Gama , Atul Prakash

Differential privacy formalises privacy-preserving mechanisms that provide access to a database. We pose the question of whether Bayesian inference itself can be used directly to provide private access to data, with no modification. The…