Filters








3,222 Hits in 2.5 sec

Privacy-Preserving Abuse Detection in Future Decentralised Online Social Networks [chapter]

Álvaro García-Recuero, Jeffrey Burdges, Christian Grothoff
2016 Lecture Notes in Computer Science  
We investigate the use of supervised learning techniques to detect abusive behavior and describe privacy-preserving protocols to compute the feature set required by abuse classification algorithms in a  ...  Future online social networks need to not only protect sensitive data of their users, but also protect them from abusive behavior coming from malicious participants in the network.  ...  Acknowledgments We thank the Renewable Freedom Foundation for supporting this research, the volunteers who annotated abuse and the anonymous reviewers.  ... 
doi:10.1007/978-3-319-47072-6_6 fatcat:ij2vso5vtve7bmzyi73dy2dhwe

Anchoring the value of Cryptocurrency [article]

Yibin Xu and Yangyu Huang and Jianhua Shao
2020 arXiv   pre-print
demands in the real world.  ...  This limitation is caused by the dilemma between high performance and decentralisation (universal joinability).  ...  and regulate the anonymous nodes by the financial mortgage. We bound the settings of Cryptocurrency with the amount of digital resources in the network.  ... 
arXiv:2001.08154v2 fatcat:oz7fa65r2bdfhftv26egt2xtqe

Anchoring the Value of Cryptocurrency

Yibin Xu, Yangyu Huang
2020 2020 IEEE International Workshop on Blockchain Oriented Software Engineering (IWBOSE)  
demands in the real world.  ...  This limitation is caused by the dilemma between high performance and decentralisation (universal joinability).  ...  and regulate the anonymous nodes by the financial mortgage. We bound the settings of Cryptocurrency with the amount of digital resources in the network.  ... 
doi:10.1109/iwbose50093.2020.9050264 fatcat:solhfb2k2bb3fa2r5whq2z2i4y

Learning to Model Opponent Learning (Student Abstract)

Ian Davies, Zheng Tian, Jun Wang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We further show that opponent modelling can improve the performance of algorithmic agents in multi-agent settings.  ...  Such an approach can reduce the variance of training signals for policy search algorithms. However, in the multi-agent setting, agents have an incentive to continually adapt and learn.  ...  policies in the decentralised setting.  ... 
doi:10.1609/aaai.v34i10.7157 fatcat:i665llqczre65dcxadzbhn3mya

Fertile soil: explaining variation in the success of Green parties

Zack P. Grant, James Tilley
2018 West European Politics  
The article also shows that regional decentralisation helps Green parties, but electoral systems have little effect on their vote share.  ...  Comparative political science has largely ignored the marked cross-national variation in Green party electoral performance.  ...  In addition, we would like to thank the anonymous reviewers of this article as well as the audience at the 2018 Political Studies Annual International Conference, where a draft of this paper was presented  ... 
doi:10.1080/01402382.2018.1521673 fatcat:te4lvt5mp5gwto5i2qzivoan5q

Learning Complex Multi-Agent Policies in Presence of an Adversary [article]

Siddharth Ghiya, Katia Sycara
2020 arXiv   pre-print
In recent years, there has been some outstanding work on applying deep reinforcement learning to multi-agent settings. Often in such multi-agent scenarios, adversaries can be present.  ...  In this work, we consider the scenario of multi-agent deception in which multiple agents need to learn to cooperate and communicate in order to deceive an adversary.  ...  This work has been funded in part by DARPA OFFSET award HR00111820029.  ... 
arXiv:2008.07698v2 fatcat:uhy7zj3d7nhbpaj5u6xymj2pda

Unravelling Ariadne's Thread: Exploring the Threats of Decentralised DNS

Constantinos Patsakis, Fran Casino, Nikolaos Lykousas, Vasilios Katos
2020 IEEE Access  
This situation has sparked a wide range of decentralisation initiatives with blockchain technology being among the most prominent and successful innovations.  ...  In this work we present the emerging threat landscape of blockchain-based DNS and we empirically validate the threats with real-world data.  ...  In this attack, the adversary tries to exploit the fact that a typo in a word may result in a word in another language.  ... 
doi:10.1109/access.2020.3004727 fatcat:wvydbzpl2zgfrjwdv3ngn7nxha

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

Lingjuan Lyu, Yitong Li, Karthik Nandakumar, Jiangshan Yu, Xingjun Ma
2020 IEEE Transactions on Dependable and Secure Computing  
In particular, we build a fair and differentially private decentralised deep learning framework called FDPDDL, which enables parties to derive more accurate local models in a fair and private manner by  ...  using our developed two-stage scheme: during the initialisation stage, artificial samples generated by Differentially Private Generative Adversarial Network (DPGAN) are used to mutually benchmark the  ...  Decentralised deep learning: Decentralised framework is much different than server-based framework, in the sense that it is purely decentralised without relying on any central servers, as exemplified in  ... 
doi:10.1109/tdsc.2020.3006287 fatcat:kwhzr3qj5vbtlehkh4areejsoa

Catching Cheats: Detecting Strategic Manipulation in Distributed Optimisation of Electric Vehicle Aggregators [article]

Alvaro Perez-Diaz, Enrico Gerding, Frank McGroarty
2020 arXiv   pre-print
In order to improve privacy and limit the need for the coordinator, we propose a reformulation of the coordination framework as a decentralised algorithm, employing the Alternating Direction Method of  ...  Given the rapid rise of electric vehicles (EVs) worldwide, and the ambitious targets set for the near future, the management of large EV fleets must be seen as a priority.  ...  All the data generated and discussed in this work is publicly available (Perez-Diaz, 2019).  ... 
arXiv:1810.07063v2 fatcat:xpbs2ikmhbcm7mjb5j67ivqjaq

Catching Cheats: Detecting Strategic Manipulation in Distributed Optimisation of Electric Vehicle Aggregators

Alvaro Perez-Diaz, Enrico Harm Gerding, Frank McGroarty
2020 The Journal of Artificial Intelligence Research  
In order to improve privacy and limit the need for the coordinator, we propose a reformulation of the coordination framework as a decentralised algorithm, employing the Alternating Direction Method of  ...  Given the rapid rise of electric vehicles (EVs) worldwide, and the ambitious targets set for the near future, the management of large EV fleets must be seen as a priority.  ...  All the data generated and discussed in this work is publicly available (Perez-Diaz, 2019).  ... 
doi:10.1613/jair.1.11573 fatcat:6sm5mzzexffqddeiwl5hoba2qu

Delegated RingCT: faster anonymous transactions [article]

Rui Morais, Paul Crocker, Simao Melo de Sousa
2020 arXiv   pre-print
reasonable trade-off for being able to develop an anonymous decentralised cryptocurrency that is faster and more scalable than existing ones.  ...  Although Delegated RingCT doesn't have the same degree of anonymity as other RingCT constructions, we argue that the benefits that the compatibility with DPoS consensus mechanisms brings constitutes a  ...  An adversary is unable to produce k + 1 non-linked valid transactions on a combined anonymity set of k input accounts.  ... 
arXiv:2011.14159v2 fatcat:6jzir3psp5dndgns6d7ezjqcuq

Learning to Model Opponent Learning [article]

Ian Davies, Zheng Tian, Jun Wang
2020 arXiv   pre-print
We further show that opponent modelling can improve the performance of algorithmic agents in multi-agent settings.  ...  Such an approach can reduce the variance of training signals for policy search algorithms. However, in the multi-agent setting, agents have an incentive to continually adapt and learn.  ...  ' policies in the decentralised setting.  ... 
arXiv:2006.03923v1 fatcat:ljhey33ubja75baqfm4f5nyena

Table of Contents

2021 2021 IEEE 34th Computer Security Foundations Symposium (CSF)  
in the Decentralised-Adversary Setting 157 Robert Künnemann (CISPA Helmholtz Center for Information Security), Deepak Garg (MPI-SWS), and Michael Backes (CISPA Helmholtz Center for Information Security  ...  Fixing the Achilles Heel of E-Voting: The Bulletin Board 125 Lucca Hirschi (Inria & LORIA), Lara Schmid (DFINITY), and David Basin (ETH Zurich) Election Verifiability Revisited: Automated Security  ... 
doi:10.1109/csf51468.2021.9535677 fatcat:rry6zpb36neixkfgty76aaifda

Unravelling Ariadne's Thread: Exploring the Threats of Decentalised DNS [article]

Constantinos Patsakis, Fran Casino, Nikolaos Lykousas, Vasilios Katos
2019 arXiv   pre-print
This has sparked a wide range of decentralisation initiatives with perhaps the most profound and successful being the blockchain technology.  ...  In this regard, we explore a part of the blockchain DNS ecosystem in terms of the browser extensions using such technologies, the chain itself (Namecoin and Emercoin), the domains, and users which have  ...  The content of this article does not reflect the official opinion of the European Union. Responsibility for the information and views expressed therein lies entirely with the authors.  ... 
arXiv:1912.03552v1 fatcat:xpefdbo3x5hvvln33ar5ubkswu

Off-Line Karma: A Decentralized Currency for Peer-to-peer and Grid Applications [chapter]

Flavio D. Garcia, Jaap-Henk Hoepman
2005 Lecture Notes in Computer Science  
We present a completely decentralised, off-line karma implementation for P2P and grid systems, that detects double-spending and other types of fraud under varying adversarial scenarios.  ...  The system is designed to allow nodes to join and leave the system at arbitrary times.  ...  Therefore, in certain situations PPay converges to a system with a centralised accounting bank.  ... 
doi:10.1007/11496137_25 fatcat:jovoh6ajzrf2vfybox3qcdx2ne
« Previous Showing results 1 — 15 out of 3,222 results