Privacy-preserved and Responsible Recommenders: From Conventional Defense to Federated Learning and Blockchain
Recommender systems (RS) play an integral role in many online platforms. Exponential
growth and potential commercial interests are raising significant concerns around privacy …
growth and potential commercial interests are raising significant concerns around privacy …
Passive Inference Attacks on Split Learning via Adversarial Regularization
Split Learning (SL) has emerged as a practical and efficient alternative to traditional
federated learning. While previous attempts to attack SL have often relied on overly strong …
federated learning. While previous attempts to attack SL have often relied on overly strong …
Veil Privacy on Visual Data: Concealing Privacy for Humans, Unveiling for DNNs
Privacy laws like GDPR necessitate effective approaches to safeguard data privacy. Existing
works on data privacy protection of DNNs mainly concentrated on the model training phase …
works on data privacy protection of DNNs mainly concentrated on the model training phase …
SAMFL: Secure Aggregation Mechanism for Federated Learning with Byzantine-robustness by functional encryption
M Guan, H Bao, Z Li, H Pan, C Huang… - Journal of Systems …, 2024 - Elsevier
Federated learning (FL) enables collaborative model training without sharing private data,
thereby potentially meeting the growing demand for data privacy protection. Despite its …
thereby potentially meeting the growing demand for data privacy protection. Despite its …
A Survey on Securing Image-Centric Edge Intelligence
Facing enormous data generated at the network edge, Edge Intelligence (EI) emerges as
the fusion of Edge Computing and Artificial Intelligence, revolutionizing edge data …
the fusion of Edge Computing and Artificial Intelligence, revolutionizing edge data …
联邦学习中的模型逆向攻防研究综述
王冬, 秦倩倩, 郭开天, 刘容轲, 颜伟鹏, 任一支… - 通信 …, 2023 - infocomm-journal.com
联邦学习作为一种分布式机器学习技术可以解决数据孤岛问题, 但机器学习模型会无意识地记忆
训练数据, 导致参与方上传的模型参数与全局模型会遭受各种隐私攻击. 针对隐私攻击中的模型 …
训练数据, 导致参与方上传的模型参数与全局模型会遭受各种隐私攻击. 针对隐私攻击中的模型 …
InvMetrics: Measuring Privacy Risks for Split Model–Based Customer Behavior Analysis
Mobile Edge Computing (MEC) has great potential to facilitate cheap and fast customer
behavior analysis (CBA). Model splitting, widely adopted in collaborative learning of MEC …
behavior analysis (CBA). Model splitting, widely adopted in collaborative learning of MEC …
Distributional Black-Box Model Inversion Attack with Multi-Agent Reinforcement Learning
A Model Inversion (MI) attack based on Generative Adversarial Networks (GAN) aims to
recover the private training data from complex deep learning models by searching codes in …
recover the private training data from complex deep learning models by searching codes in …
UIFV: Data Reconstruction Attack in Vertical Federated Learning
Vertical Federated Learning (VFL) facilitates collaborative machine learning without the
need for participants to share raw private data. However, recent studies have revealed …
need for participants to share raw private data. However, recent studies have revealed …
Privacy-preserving Compression for Efficient Collaborative Inference
Collaborative inference accelerates DNN inference tasks of resource-limited devices (eg,
clients) by offloading model slices to resource-rich devices (eg, servers). During the …
clients) by offloading model slices to resource-rich devices (eg, servers). During the …