中文
相关论文

相关论文: Controlling the privacy loss with the input featur…

200 篇论文

The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the…

密码学与安全 · 计算机科学 2025-08-20 Jinyu Lu , Xinrong Sun , Yunting Tao , Tong Ji , Fanyu Kong , Guoqiang Yang

In this paper, we propose a model protection method for convolutional neural networks (CNNs) with a secret key so that authorized users get a high classification accuracy, and unauthorized users get a low classification accuracy. The…

计算机视觉与模式识别 · 计算机科学 2021-09-02 MaungMaung AprilPyone , Hitoshi Kiya

Subjective interpretation and content diversity make predicting whether an image is private or public a challenging task. Graph neural networks combined with convolutional neural networks (CNNs), which consist of 14,000 to 500 millions…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Alessio Xompero , Andrea Cavallaro

Privacy-preserving inference of convolutional neural networks (CNNs) using homomorphic encryption has emerged as a promising approach for enabling secure machine learning in untrusted environments. In our previous work, we introduced a…

密码学与安全 · 计算机科学 2025-12-23 John Chiang

We propose a novel decentralized feature extraction approach in federated learning to address privacy-preservation issues for speech recognition. It is built upon a quantum convolutional neural network (QCNN) composed of a quantum circuit…

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNN) possible. However, the performance of these methods remain limited by their heavy…

密码学与安全 · 计算机科学 2026-02-10 Eduardo Chielle , Manaar Alam , Jinting Liu , Jovan Kascelan , Michail Maniatakos

Convolutional Neural Networks (CNNs) have proven to be a powerful state-of-the-art method for image classification tasks. One drawback however is the high computational complexity and high memory consumption of CNNs which makes them…

计算机视觉与模式识别 · 计算机科学 2021-02-04 Rishabh Goyal , Joaquin Vanschoren , Victor van Acht , Stephan Nijssen

The widespread deployment of surveillance cameras for facial recognition gives rise to many privacy concerns. This study proposes a privacy-friendly alternative to large scale facial recognition. While there are multiple techniques to…

计算机视觉与模式识别 · 计算机科学 2021-01-28 Mattijs Baert , Sam Leroux , Pieter Simoens

In the current era, biometric based access control is becoming more popular due to its simplicity and ease to use by the users. It reduces the manual work of identity recognition and facilitates the automatic processing. The face is one of…

计算机视觉与模式识别 · 计算机科学 2019-03-28 Chaitanya Nagpal , Shiv Ram Dubey

This paper proposes a visual encryption method to ensure the confidentiality of digital images. The model used is based on an autoencoder using aConvolutional Neural Network (CNN) to ensure the protection of the user data on both the sender…

密码学与安全 · 计算机科学 2025-04-02 Mahdi Madani , El-Bay Bourennane

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing,…

机器学习 · 计算机科学 2021-08-31 Giosuè Cataldo Marinò , Alessandro Petrini , Dario Malchiodi , Marco Frasca

Incorporating fully homomorphic encryption (FHE) into the inference process of a convolutional neural network (CNN) draws enormous attention as a viable approach for achieving private inference (PI). FHE allows delegating the entire…

密码学与安全 · 计算机科学 2023-10-26 Jaiyoung Park , Donghwan Kim , Jongmin Kim , Sangpyo Kim , Wonkyung Jung , Jung Hee Cheon , Jung Ho Ahn

Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods…

机器学习 · 计算机科学 2020-05-26 Hang Li , Chen Ma , Wei Xu , Xue Liu

Channel pruning is widely used to reduce the complexity of deep network models. Recent pruning methods usually identify which parts of the network to discard by proposing a channel importance criterion. However, recent studies have shown…

计算机视觉与模式识别 · 计算机科学 2022-10-04 Yuanzhi Duan , Yue Zhou , Peng He , Qiang Liu , Shukai Duan , Xiaofang Hu

Face recognition based on the deep convolutional neural networks (CNN) shows superior accuracy performance attributed to the high discriminative features extracted. Yet, the security and privacy of the extracted features from deep learning…

计算机视觉与模式识别 · 计算机科学 2022-06-10 Xingbo Dong , Zhihui Miao , Lan Ma , Jiajun Shen , Zhe Jin , Zhenhua Guo , Andrew Beng Jin Teoh

Deep convolutional neural networks (CNN) has become the most promising method for object recognition, repeatedly demonstrating record breaking results for image classification and object detection in recent years. However, a very deep CNN…

计算机视觉与模式识别 · 计算机科学 2014-12-22 Yunchao Gong , Liu Liu , Ming Yang , Lubomir Bourdev

Convolutional Neural Networks (CNNs) has been applied in numerous Internet of Things (IoT) devices for multifarious downstream tasks. However, with the increasing amount of data on edge devices, CNNs can hardly complete some tasks in time…

计算机视觉与模式识别 · 计算机科学 2022-08-11 Zidu Wang , Xuexin Liu , Long Huang , Yunqing Chen , Yufei Zhang , Zhikang Lin , Rui Wang

Recently, deep learning methods have been proposed for quantitative susceptibility mapping (QSM) data processing: background field removal, field-to-source inversion, and single-step QSM reconstruction. However, the conventional padding…

计算机视觉与模式识别 · 计算机科学 2021-06-30 Juan Liu

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We…

图像与视频处理 · 电气工程与系统科学 2022-10-04 Bardia Azizian , Ivan V. Bajić

Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy…

机器学习 · 计算机科学 2020-01-15 Liyao Xiang , Haotian Ma , Hao Zhang , Yifan Zhang , Jie Ren , Quanshi Zhang
‹ 上一页 1 2 3 10 下一页 ›