-
Article
Privacy preserving machine unlearning for smart cities
Due to emerging concerns about public and private privacy issues in smart cities, many countries and organizations are establishing laws and regulations (e.g., GPDR) to protect the data security. One of the mo...
-
Chapter and Conference Paper
Member Inference Attacks in Federated Contrastive Learning
In the past, the research community has studied privacy issues in federated learning, self-supervised learning, and deep models. However, privacy investigations into the domain of federated contrast learning a...
-
Article
Model architecture level privacy leakage in neural networks
Privacy leakage is one of the most critical issues in machine learning and has attracted growing interest for tasks such as demonstrating potential threats in model attacks and creating model defenses. In rece...
-
Article
Open AccessPoint-wise spatial network for identifying carcinoma at the upper digestive and respiratory tract
Artificial intelligence has been widely investigated for diagnosis and treatment strategy design, with some models proposed for detecting oral pharyngeal, nasopharyngeal, or laryngeal carcinoma. However, no co...
-
Chapter and Conference Paper
Data Reconstruction from Gradient Updates in Federated Learning
Federated learning has become an emerging technology to protect data privacy in the distributed learning area, by kee** each client user’s data locally. However, recent work shows that client users’ data mig...
-
Chapter and Conference Paper
Data Leakage with Label Reconstruction in Distributed Learning Environments
Distributed learning is commonly applied for the high demands of computation resources while training models with large-scale data. However, existing solutions revealed that it may lead to information leakage ...
-
Article
CRSM: a practical crowdsourcing-based road surface monitoring system
Detecting road potholes and road roughness levels is key to road condition monitoring, which impacts transport safety and driving comfort. We propose a crowdsourcing-based road surface monitoring system, simpl...