Filters








1,344 Hits in 5.5 sec

Adversary-resilient Distributed and Decentralized Statistical Inference and Machine Learning [article]

Zhixiong Yang, Arpita Gang, Waheed U. Bajwa
2020 arXiv   pre-print
While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual  ...  As a result, we now have a plethora of algorithmic approaches that guarantee robustness of distributed and/or decentralized inference and learning under different adversarial threat models.  ...  ACKNOWLEDGEMENTS The authors gratefully acknowledge the support of the NSF (CCF-1453073, CCF-1907658), the ARO (W911NF-17-1-0546), and the DARPA Lagrange Program (ONR/SPAWAR contract N660011824020).  ... 
arXiv:1908.08649v2 fatcat:de356dvwinfv5g5njo64qmzpvi

Byzantine Fault Tolerance in Distributed Machine Learning : a Survey [article]

Djamila Bouhata, Hamouma Moumen
2022 arXiv   pre-print
Byzantine Fault Tolerance (BFT) is among the most challenging problems in Distributed Machine Learning (DML).  ...  However, certain aspects seem to be limited, such as the few analyzed approaches and the absence of the techniques classification employed in the studied approaches.  ...  [101] studied the issue of Byzantine-resilient distributed machine learning in a decentralized architecture.  ... 
arXiv:2205.02572v1 fatcat:h2hkcgz3w5cvrnro6whl2rpvby

Vulnerabilities in Federated Learning

Nader Bouacida, Prasant Mohapatra
2021 IEEE Access  
A new decentralized training paradigm, known as Federated Learning (FL), enables multiple clients located at different geographical locations to learn a machine learning model collaboratively without sharing  ...  Therefore, it is crucial to raise awareness of the consequences resulting from the new threats to FL systems. To date, the security of traditional machine learning systems has been widely examined.  ...  The emergence of large-scale multi-party machine learning workloads and distributed ledgers for scalable consensus can offer practical solutions to peer-to-peer FL.  ... 
doi:10.1109/access.2021.3075203 doaj:5e62c955db514036939a1c65011f46b8 fatcat:viv7tij6cffnlev4l52wggkxfe

BEAS: Blockchain Enabled Asynchronous Secure Federated Machine Learning [article]

Arup Mondal, Harpreet Virk, Debayan Gupta
2022 arXiv   pre-print
Federated Learning (FL) enables multiple parties to distributively train a ML model without revealing their private datasets.  ...  We also define a novel protocol to prevent premature convergence in heterogeneous learning environments.  ...  well as ensure resiliency from adversaries.  ... 
arXiv:2202.02817v1 fatcat:lzwiv3bysrgyvmff2tqxxmm4lm

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey [article]

Shangwei Guo, Xu Zhang, Fei Yang, Tianwei Zhang, Yan Gan, Tao Xiang, Yang Liu
2021 arXiv   pre-print
With the rapid demand of data and computational resources in deep learning systems, a growing number of algorithms to utilize collaborative machine learning techniques, for example, federated learning,  ...  And a large amount of works have been proposed to maintain the model integrity and mitigate the privacy leakage of training data during the training phase for different collaborative learning systems.  ...  the ability to do machine learning from the need to store the data in the cloud.  ... 
arXiv:2112.10183v1 fatcat:ujfz4a5mdrhsbk4kiqoqo2snfe

Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges [article]

Solmaz Niknam, Harpreet S. Dhillon, Jeffery H. Reed
2020 arXiv   pre-print
There is a growing interest in the wireless communications community to complement the traditional model-based design approaches with data-driven machine learning (ML)-based solutions.  ...  In this article, we provide an accessible introduction to the general idea of federated learning, discuss several possible applications in 5G networks, and describe key technical challenges and open problems  ...  Poisoning resilience defense mechanisms are urgently required, as federated learning in its primary form is susceptible to such adversarial attacks.  ... 
arXiv:1908.06847v4 fatcat:plfaupfexzd5bb3o72f3z5kskm

Machine Learning Systems for Intelligent Services in the IoT: A Survey [article]

Wiebke Toussaint, Aaron Yi Ding
2020 arXiv   pre-print
Machine learning (ML) technologies are emerging in the Internet of Things (IoT) to provision intelligent services.  ...  It covers the latest developments (up to 2020) on scaling and distributing ML across cloud, edge, and IoT devices.  ...  Learning under label noise [122] and adversarial machine learning [71] , which studies the behaviour of machine learning techniques when subjected to the malicious attack of an adversary, have been  ... 
arXiv:2006.04950v3 fatcat:xrjcioqkrrhpvgmwmutiajgfbe

Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS

Felix O. Olowononi, Danda B. Rawat, Chunmei Liu
2020 IEEE Communications Surveys and Tutorials  
One of the dominant methodologies explored for building resilient CPS is dependent on machine learning (ML) algorithms.  ...  However, in a world of increasing adversaries, it is becoming more difficult to totally prevent CPS from adversarial attacks, hence the need to focus on making CPS resilient.  ...  OVERVIEW OF MACHINE LEARNING In order to give the reader a good grasp of the discussion on the role of ML in CPS and the need to make ML models resilient to adversarial attacks, the various ML models commonly  ... 
doi:10.1109/comst.2020.3036778 fatcat:tyrz76ofxfejha5kwhoptv2hwu

Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness [article]

Yuwei Sun, Hideya Ochiai, Hiroshi Esaki
2021 arXiv   pre-print
Decentralized deep learning (DDL) such as federated learning and swarm learning as a promising solution to privacy-preserving data processing for millions of smart edge devices, leverages distributed computing  ...  In this survey paper, we demonstrate the technical fundamentals of DDL that benefit many walks of society through decentralized learning.  ...  Shekita, and B. Su, “Scaling distributed machine learning [30] Y. Lu, X. Huang, Y. Dai, S. Maharjan, and Y.  ... 
arXiv:2108.03980v4 fatcat:3chrjozkxrdzljthkjzlagg6uy

WAFFLE: Watermarking in Federated Learning [article]

Buse Gul Atli, Yuxi Xia, Samuel Marchal, N. Asokan
2021 arXiv   pre-print
Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides.  ...  By avoiding the need to transport the training data to the central server, federated learning improves privacy and efficiency.  ...  Federated learning [1] is an instance of privacy-preserving distributed machine learning that allows decentralized training of deep neural networks (DNNs) by many parties holding local This work was  ... 
arXiv:2008.07298v3 fatcat:mkjyzabzyjda3bodjcok73kgfu

On the Security Privacy in Federated Learning [article]

Gorka Abad, Stjepan Picek, Víctor Julio Ramírez-Durán, Aitor Urbieta
2022 arXiv   pre-print
Recent privacy awareness initiatives such as the EU General Data Protection Regulation subdued Machine Learning (ML) to privacy and security assessments.  ...  Federated Learning (FL) grants a privacy-driven, decentralized training scheme that improves ML models' security.  ...  ., adversarial machine learning, the authors [19] developed ensemble pre-trained adversarial models for transferring the adverse effect to a target model.  ... 
arXiv:2112.05423v2 fatcat:qcovp2cz2rfgbcvx6mtx5xighe

OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning [article]

Jiacheng Liang, Songze Li, Bochuan Cao, Wensi Jiang, Chaoyang He
2021 arXiv   pre-print
We propose OmniLytics, a blockchain-based secure data trading marketplace for machine learning applications.  ...  data owners who provide faulty results to poison model training; and 4) resilience to malicious model owners who intend to evade payment.  ...  Current strategies to defend Byzantine clients mainly follow distributed machine learning protocols designed under adversarial settings (Blanchard et al. 2017a; Chen, Su, and Xu 2017; Yin et al. 2018;  ... 
arXiv:2107.05252v4 fatcat:u2uaa4fbrvdb3jqbipttcmtvq4

Separation of Powers in Federated Learning [article]

Pau-Chen Cheng, Kevin Eykholt, Zhongshu Gu, Hani Jamjoom, K. R. Jayaram, Enriquillo Valdez, Ashish Verma
2021 arXiv   pre-print
In this paper, we introduce TRUDA, a new cross-silo FL system, employing a trustworthy and decentralized aggregation architecture to break down information concentration with regard to a single aggregator  ...  This challenge is especially acute due to recently demonstrated attacks that have reconstructed large fractions of training data from ostensibly "sanitized" model updates.  ...  For example, Software Guard Extensions (SGX) has been leveraged to support secure model inference [15, 52] , privacy-preserving multiparty machine learning [16, 20, 21, 40, 43] , and analytics on sensitive  ... 
arXiv:2105.09400v1 fatcat:ewbxs33eijfx5fsbmnsi62odl4

Advances and Open Problems in Federated Learning [article]

Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G.L. D'Oliveira, Hubert Eichner (+47 others)
2021 arXiv   pre-print
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science  ...  Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service  ...  Acknowledgments The authors would like to thank Alex Ingerman and David Petrou for their useful suggestions and insightful comments during the review process.  ... 
arXiv:1912.04977v3 fatcat:efkbqh4lwfacfeuxpe5pp7mk6a

Systematic Evaluation of Privacy Risks of Machine Learning Models [article]

Liwei Song, Prateek Mittal
2020 arXiv   pre-print
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model  ...  Our work emphasizes the importance of a systematic and rigorous evaluation of privacy risks of machine learning models.  ...  Young Investigator Prize, Faculty research award from Facebook, and by Schmidt DataX award.  ... 
arXiv:2003.10595v2 fatcat:yqiijqg4zneu5mtynmwaivpiy4
« Previous Showing results 1 — 15 out of 1,344 results