Filters








29,715 Hits in 4.4 sec

Privacy Threats Analysis to Secure Federated Learning [article]

Yuchen Li, Yifan Bao, Liyao Xiang, Junhan Liu, Cen Chen, Li Wang, Xinbing Wang
2021 arXiv   pre-print
In this paper, we analyze the privacy threats in industrial-level federated learning frameworks with secure computation, and reveal such threats widely exist in typical machine learning models such as  ...  However, we found that despite the efforts, federated learning remains privacy-threatening, due to its interactive nature across different parties.  ...  CONCLUSION We reveal in this paper that privacy threats widely exist in today's secure federated learning framework, regardless the secure computation protocols implemented.  ... 
arXiv:2106.13076v1 fatcat:lg5crf4m7vbjvny3ud6tb5pcmu

Blockchain-based Collaborated Federated Learning for Improved Security, Privacy and Reliability [article]

Amir Afaq, Zeeshan Ahmed, Noman Haider, Muhammad Imran
2022 arXiv   pre-print
Federated Learning (FL) provides privacy preservation by allowing the model training at edge devices without the need of sending the data from edge to a centralized server.  ...  Another variant of FL which is well suited for the Internet of Things (IoT) is known as Collaborated Federated Learning (CFL), which does not require an edge device to have a direct link to the model aggregator  ...  In the proposed research work, we intend to use block chain for CFL (BlockCFL) and study it's performance advantages in the context of security, reliability and privacy.  ... 
arXiv:2201.08551v1 fatcat:urdgdb2nerhxhjoynrkhnryqem

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Mohamed Amine Ferrag, Othmane Friha, Leandros Maglaras, Helge Janicke, Lei Shu
2021 IEEE Access  
. • Threat models in federated learning: It indicates whether the survey considered threat models in federated learning-based frameworks for cyber security in IoT. • Experimental analysis in IoT: It indicates  ...  [34] provided a comprehensive survey on privacy threats of federated learning, but without an experimental analysis in IoT networks. Kholod et al.  ...  His research interests include wireless network security, network coding security, and applied cryptography.  ... 
doi:10.1109/access.2021.3118642 fatcat:222fgsvt3nh6zcgm5qt4kxe7c4

A Contemplative Perspective on Federated Machine Learning: Taxonomy, Threats & Vulnerability Assessment and Challenges

Divya Jatain, Vikram Singh, Naveen Dahiya
2021 Journal of King Saud University: Computer and Information Sciences  
This paper intends to provide a complete picture by giving an in-depth and comprehensive analysis of Federated Learning and its taxonomy.  ...  However, in the aftermath of a data breach by Facebook in 2018, there are some serious concerns over user data privacy and security being used to train the Machine Learning models.  ...  Acknowledgements: The authors would like to extend their gratitude towards Chaudhary Devi Lal University, Sirsa, India and Maharaja Surajmal Institute of Technology, New Delhi, India for providing the  ... 
doi:10.1016/j.jksuci.2021.05.016 fatcat:6gynsax3xreyfit5vlyyno3jiy

AI-Driven Security Solutions for the Internet of Everything

Deepak Puthal, Amit Mishra, Suraj Sharma
2021 IEEE Consumer Electronics Magazine  
The article "RR-LADP: A privacyenhanced federated learning scheme for Internet of Everything" proposes privacy-aware federated learning for IoE by adopting two mechanisms, i.e.,  ...  Federated learning is another recent innovation providing a methodology to have machine learning algorithms for edge-learning for IoE.  ...  The article "RR-LADP: A privacyenhanced federated learning scheme for Internet of Everything" proposes privacy-aware federated learning for IoE by adopting two mechanisms, i.e., Guest Editors' Introduction  ... 
doi:10.1109/mce.2021.3071676 fatcat:663acipcprfavpv5d33paiyjoa

Analysis on Security and Privacy-preserving in Federated Learning

Jipeng Li, Xinyi Li, Chenjing Zhang
2022 Highlights in Science Engineering and Technology  
This paper first introduces the types of federated learning, including horizontal federated learning, vertical federated learning and federated transfer learning, and then analyses the existing security  ...  Federated Learning has been an effective tool for the protection of privacy.  ...  This paper analyses the security problems that may arise from federated learning, focuses on the security threats of poisoning attacks, countermeasures and privacy leaks, and summarizes the defence measures  ... 
doi:10.54097/hset.v4i.923 fatcat:qa4j6civbrdklgg5fyksce4vna

Federated Learning Versus Classical Machine Learning: A Convergence Comparison [article]

Muhammad Asad, Ahmed Moustafa, Takayuki Ito
2021 arXiv   pre-print
Simultaneously, increasing privacy threats in trending applications led to the redesign of classical data training models.  ...  To this end, federated learning has achieved significant importance over distributed data training.  ...  In particular, the authors briefly explained the threat model for machine learning and proposed the desired properties to improve the security and privacy threats.  ... 
arXiv:2107.10976v1 fatcat:s5dtxqdylnfpnpxwavjmoqoosi

Deliverable D5.1 Specification of security framework and trust management platform

Drasko Draskovic, Dusan Borovcanin, Srdjan Penjivrag, Francois Carrez, S. Abdelkareem, Spiros Roumpis, Vera Stavroulaki, Panagiotis Demestichas
2021 Zenodo  
Federated learning global models for security and data protection threat detection and classification Federated learning mechanisms implemented Implemented federated learning mechanisms for multiple system  ...  D5.1 will specify a federated learning mechanism for distributed training of machine learning models for threat detection and classification.  ...  Federated learning approach for threat analysis model In order to increase security and privacy-preserving guarantees, the use of federated ML will be used in the proposed DEDICAT 6G framework.  ... 
doi:10.5281/zenodo.6780076 fatcat:5tudbc5bf5ddhfqvvnjvye32vy

Is It Possible to Preserve Privacy in the Age of AI?

Vijayanta Jain, Sepideh Ghanavati
2020 Web Search and Data Mining  
The increasing prevalence of AI promotes data collection and consequently poses a threat to privacy.  ...  However, as training artificially intelligent models require a large amount of data, it poses a threat to user privacy.  ...  This work surveys the existing literature to identify the security and privacy threats as well as defenses that have been developed to mitigate the threats.  ... 
dblp:conf/wsdm/JainG20 fatcat:2onflyckjfdanlh2ebwpxxcpke

Security, Trust, and Privacy in Machine Learning-Based Internet of Things

Weizhi Meng, Wenjuan Li, Jinguang Han, Chunhua Su
2022 Security and Communication Networks  
We believe that this Special Issue can provide useful hints on how to address security, privacy, and trust issues in machine learning-based IoT environments.  ...  Acknowledgments We would like to take this opportunity to thank the Chief Editor Dr. Di Pietro and all staff from Security and Communication Networks, for supporting and guiding this Special Issue.  ...  on discussing the security, trust, and privacy challenges in machine learning-based IoT. e potential topics focus on the application of machine learning techniques to address security, privacy, and trust  ... 
doi:10.1155/2022/9851463 fatcat:pyvkvmfcarcrxmo6fjppjxv4cq

MUSKETEER D3.2 Architecture Design – Final Version

Mark Purcell, Mathieu Sinn, Marco Simioni, Stefano Braghin, Minh Ngoc Tran
2020 Zenodo  
This document describing the final version of the MUSKETEER platform architecture, how it meets the final requirements of the federated and privacy-preserving machine learning services, how it addresses  ...  It is the culmination of task T3.1 and builds upon the initial architecture document D3.1, providing architecture/design updates as well as reporting progress in relation to the platform requirements.  ...  -in so far as the platform has to provide the core capabilities to support the deployment of the proposed algorithms. • D5.1 Threat analysis for federated machine learning algorithms -in so far as the  ... 
doi:10.5281/zenodo.4729775 fatcat:23cos3j4fbfozl56mgq3tytbxe

Secure Multi-Party Computation based Privacy Preserving Data Analysis in Healthcare IoT Systems [article]

Kevser Şahinbaş, Ferhat Ozgur Catak
2021 arXiv   pre-print
In this study, it is aimed to propose a model to handle the privacy problems based on federated learning. Besides, we apply secure multi party computation.  ...  However, the data transferred to the digital environment pose a threat of privacy leakage.  ...  In Section 4, we present an extensive of privacy analysis and performance evaluation. Section 5 shows threats to validity. Lastly, we conclude the chapter at Section 6.  ... 
arXiv:2109.14334v1 fatcat:lrwbkaxbezgw5kz3xtgqaf2sgm

Privacy Threats Against Federated Matrix Factorization [article]

Dashan Gao, Ben Tan, Ce Ju, Vincent W. Zheng, Qiang Yang
2020 arXiv   pre-print
Federated learning provides the possibility to bridge the data silos and build machine learning models without compromising privacy and security.  ...  However, the privacy threats in federated matrix factorization are not studied.  ...  Privacy Preservation in Federated MF According to the privacy threats investigated in section 4, we give some advises for privacy preservation in federated MF.  ... 
arXiv:2007.01587v1 fatcat:kevu5w6hxrc2vkzfwhvin6imhu

MUSKETEER D5.1 Threat analysis for federated machine learning algorithms

Luis Muñoz-González
2019 Zenodo  
It also contains the analysis of the threats across the different Privacy Operation Modes (POMs) to be implemented for MUSKETEER platform.  ...  design, deployment and testing of federated machine learning algorithms.  ...  Machine Learning to Augment Shared Knowledge in Federated Privacy-Preserving Scenarios (MUSKETEER) Executive Summary This deliverable D5.1 -Threat analysis for federated machine learning algorithms -  ... 
doi:10.5281/zenodo.4736943 fatcat:2zealgae7rhsjecbg4q4vnb72i

Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors [article]

Timothy Stevens, Christian Skalka, Christelle Vincent, John Ring, Samuel Clark, Joseph Near
2021 arXiv   pre-print
Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge.  ...  We present a new federated learning protocol that leverages a novel differentially private, malicious secure aggregation protocol based on techniques from Learning With Errors.  ...  Combining secure aggregation [8, 11] with differential privacy [19, 26] ensures end-to-end privacy in federated learning systems.  ... 
arXiv:2112.06872v1 fatcat:k2cbkzojcvfybabfhzttk6gk2i
« Previous Showing results 1 — 15 out of 29,715 results