Differential privacy for deep and federated learning: A survey
A El Ouadrhiri, A Abdelhadi - IEEE access, 2022 - ieeexplore.ieee.org
Users' privacy is vulnerable at all stages of the deep learning process. Sensitive information
of users may be disclosed during data collection, during training, or even after releasing the …
of users may be disclosed during data collection, during training, or even after releasing the …
Privacy-preserving techniques in recommender systems: state-of-the-art review and future research agenda
D Pramod - Data Technologies and Applications, 2022 - emerald.com
Purpose This study explores privacy challenges in recommender systems (RSs) and how
they have leveraged privacy-preserving technology for risk mitigation. The study also …
they have leveraged privacy-preserving technology for risk mitigation. The study also …
[HTML][HTML] Digestive neural networks: A novel defense strategy against inference attacks in federated learning
Federated Learning (FL) is an efficient and secure machine learning technique designed for
decentralized computing systems such as fog and edge computing. Its learning process …
decentralized computing systems such as fog and edge computing. Its learning process …
SVeriFL: Successive verifiable federated learning with privacy-preserving
H Gao, N He, T Gao - Information Sciences, 2023 - Elsevier
With federated learning, one of the most notable features is that it can update global model
parameter without using the users' local data. However, various security and privacy …
parameter without using the users' local data. However, various security and privacy …
Blockchain based decentralized learning for security in digital twins
Z Lv, C Cheng, H Lv - IEEE Internet of Things Journal, 2023 - ieeexplore.ieee.org
This work aims to analyze malicious communication behaviors that pose a threat to the
security of digital twins (DTs) and safeguard user privacy. A unified and integrated …
security of digital twins (DTs) and safeguard user privacy. A unified and integrated …
A comprehensive survey on privacy-preserving techniques in federated recommendation systems
Big data is a rapidly growing field, and new developments are constantly emerging to
address various challenges. One such development is the use of federated learning for …
address various challenges. One such development is the use of federated learning for …
Privacy-preserving credit evaluation system based on blockchain
Y Qiao, Q Lan, Z Zhou, C Ma - Expert Systems with Applications, 2022 - Elsevier
In digital intelligence era, the authenticity of data and the privacy protection of data sharing
and multiparty collaborative computing are key factors in building a good credit evaluation …
and multiparty collaborative computing are key factors in building a good credit evaluation …
Federated anomaly analytics for local model poisoning attack
The local model poisoning attack is an attack to manipulate the shared local models during
the process of distributed learning. Existing defense methods are passive in the sense that …
the process of distributed learning. Existing defense methods are passive in the sense that …
Verifiable federated learning with privacy-preserving data aggregation for consumer electronics
H Xie, Y Wang, Y Ding, C Yang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the development of information technology, massive and heterogeneous consumer
electronic products can access the network. These products may engage third-party servers …
electronic products can access the network. These products may engage third-party servers …
Power-intent systolic array using modified parallel multiplier for machine learning acceleration
Systolic arrays are an integral part of many modern machine learning (ML) accelerators due
to their efficiency in performing matrix multiplication that is a key primitive in modern ML …
to their efficiency in performing matrix multiplication that is a key primitive in modern ML …