A5005526474- Privacy-Preserving Technologies in Data
- Cryptography and Data Security
- Privacy, Security, and Data Protection
- Mobile Crowdsensing and Crowdsourcing
- Advanced Neural Network Applications
- Stochastic Gradient Optimization Techniques
- Adversarial Robustness in Machine Learning
- Human Mobility and Location-Based Analysis
- Vehicular Ad Hoc Networks (VANETs)
- Blockchain Technology Applications and Security
- Transportation and Mobility Innovations
- Access Control and Trust
- IoT and Edge/Fog Computing
- Chaos-based Image/Signal Encryption
- Cloud Data Security Solutions
Fujian Normal University
2020-2024
Xidian University
2023-2024
State Key Laboratory of Cryptology
2023
Guilin University of Electronic Technology
2021-2022
Guizhou University
2022
State of The Art
2020
Federated learning of deep neural networks has emerged as an evolving paradigm for distributed machine learning, gaining widespread attention due to its ability update parameters without collecting raw data from users, especially in digital healthcare applications. However, the traditional centralized architecture federated suffers several problems (e.g., single point failure, communication bottlenecks, etc.), malicious servers inferring gradients and causing gradient leakage. To tackle...
Data sharing among connected and autonomous vehicles without any protection will cause private information leakage. Simply encrypting data introduces a heavy overhead; most importantly, when encrypted (ciphertext) is decrypted on vehicle, the receiver be fully aware of sender's data, implying potential To tackle these issues, we propose an edge-assisted privacy-preserving raw framework. First, leverage additive secret technique to encrypt into two ciphertexts construct classes secure...
Collaborative perception enables autonomous vehicles to exchange sensor data among each other achieve cooperative object classification, which is considered an effective means improve the accuracy of connected (CAVs). To protect information privacy in perception, we propose a lightweight, privacy-preserving classification framework that allows CAVs raw (e.g., images captured by HD camera), without leaking private information. Leveraging chaotic encryption and additive secret sharing...
Connected autonomous vehicles (CAVs) are capable of capturing high-definition images from onboard sensors, which can be used to facilitate the detection objects in vicinity. Such may, however, contain sensitive information (e.g., human faces and license plates) as well indirect location CAVs. To protect object privacy shared by CAVs, this article proposes a privacy-preserving (P2OD) framework. Specifically, we propose multiple secure computing protocols designed construct Faster...
Connected autonomous vehicles (CAVs) employ the point cloud data captured by LiDAR to enhance capability of object recognition and detection. Edge computing with its inherent advantages can help CAVs alleviate resource constraints enable faster situational awareness processing. However, contains private information, such as vehicle identity, location trajectory, directly uploading raw edge nodes or other will lead serious privacy leakage. To best our knowledge, we are first try tackle this...
Although data sharing and fusion between connected autonomous vehicles (CAVs) can effectively enhance environment awareness improve driving safety, it has to face severe challenges of privacy disclosure. Outsourcing encrypted edge servers for analysis model learning alleviate this issue without imposing additional computing load on CAVs. In article, we propose a privacy-preserving outsourcing (PPOL) framework based lightweight additive secret (ASS). Firstly, object detection method over...
Outsourced cloud computing can be considered as an effective way to overcome the data island among users and relieve pressure of limited resources. However, due concerns about trust in servers, outsourcing users' model training task has considerable privacy disclosure risks. This article presents a PriKPM scheme by using additive secret sharing (ASS), so implement privacy-preserving <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">...
It is enormously challenging to achieve a satisfactory balance between quality of service (QoS) and users’ privacy protection along with measuring disclosure in social Internet Things (IoT). We propose privacy-preserving personalized framework (Persian) based on static Bayesian game provide according individual security requirements IoT. Our approach quantifies preferences uses fuzzy uncertainty reasoning classify users. These classification results facilitate trustworthy cloud providers...
With the maturity and development of 5G field, Mobile Edge CrowdSensing (MECS), as an intelligent data collection paradigm, provides a broad prospect for various applications in IoT. However, sensing users uploaders lack balance between benefits privacy threats, leading to conservative uploads low revenue or excessive breaches. To solve this problem, Dynamic Privacy Measurement Protection (DPMP) framework is proposed based on differential reinforcement learning. Firstly, DPM model designed...
Aiming to the data and model privacy issue in outsourced clustering tasks, this paper proposes an practical privacy-preserving k-prototype scheme (referred PriKPM) supporting mixed numerical categorical attributes data. In PriKPM scheme, users only randomly split sample into two shares send them non-collusive servers, without interacting with servers online. The can cooperate perform secure distance calculation, cluster center selection, in-cluster update operations over randomness shares,...
The connected autonomous vehicles (CAVs) are a key component of intelligent transportation systems (ITS) where communicate with each other to exchange sensing data from on-board sensors (e.g., high-definition cameras and lidar). For the sake category location privacy leakage images shared by CAVs computational inefficiency privacy-preserving object detection framework in edge computing environment, we propose lightweight (PPDF) support secure extraction, classification image features,...