Machine un-learning: an overview of techniques, applications, and future directions
ML applications proliferate across various sectors. Large internet firms employ ML to train
intelligent models using vast datasets, including sensitive user information. However, new …
intelligent models using vast datasets, including sensitive user information. However, new …
Privacy-preserving swarm learning based on homomorphic encryption
Swarm learning is a decentralized machine learning method that combines edge computing,
blockchain based point-to-point network and coordination while maintaining consistency …
blockchain based point-to-point network and coordination while maintaining consistency …
Defending against model extraction attacks with OOD feature learning and decision boundary confusion
C Liang, J Huang, Z Zhang, S Zhang - Computers & Security, 2024 - Elsevier
Recent studies have demonstrated that Deep Neural Networks (DNNs) are vulnerable to
model extraction attacks. In these attacks, the malicious users utilize Out-Of-Distribution …
model extraction attacks. In these attacks, the malicious users utilize Out-Of-Distribution …
Accuracy-Tweakable Federated Learning with Minimal Interruption
C Troiani, Y Li, W Susilo… - … Conference on Data …, 2023 - ieeexplore.ieee.org
Federated machine learning plays a significant role in pivotal industries such as health,
finance and Internet-of-Things. Not needing to share training data makes it appealing for …
finance and Internet-of-Things. Not needing to share training data makes it appealing for …
Reducing model memorization to mitigate membership inference attacks
M Sheikhjaberi, D Alhadidi - … on Trust, Security and Privacy in …, 2023 - ieeexplore.ieee.org
Given a machine learning model and a record, membership inference attacks determine
whether this record was used as part of the model's training dataset. This can raise privacy …
whether this record was used as part of the model's training dataset. This can raise privacy …
Critical Analysis of Privacy Risks in Machine Learning and Implications for Use of Health Data: A systematic review and meta-analysis on membership inference …
EV Walker, J Bu, M Pakseresht, M Wickham, L Shack… - 2023 - researchsquare.com
Purpose. Machine learning (ML) has revolutionized data processing and analysis, with
applications in health showing great promise. However, ML poses privacy risks, as models …
applications in health showing great promise. However, ML poses privacy risks, as models …