TY - JOUR
T1 - AntiCheetah
T2 - Trustworthy computing in an outsourced (cheating) environment
AU - Di Pietro, Roberto
AU - Lombardi, Flavio
AU - Martinelli, Fabio
AU - Sgandurra, Daniele
N1 - Funding Information:
The authors would like to thank the anonymous reviewers for their comments, which helped improving the quality of the paper. Roberto Di Pietro is Head of the Cyber Security Research Dept. at Bell Labs, France. He graduated at Università di Pisa in 1994, and received the Ph.D. in Computer Science at Sapienza Università di Roma in 2004. In 2005 he was presented with the ERCIM (European Research Consortium for Informatics and Mathematics) fellowship. He has been spending several long periods abroad (EURECOM, UNESCO Chair in Data Privacy, Vrije Universiteit). He was appointed Chair of Excellence from University Carlos III, Madrid, for the Academic Year 2011/2012. His main research interests include Cyber Security, security and privacy of distributed systems, cloud computing virtualization and security, computer forensics, computer and network security, and role mining, publishing in Intl. Journals and Conference proceedings 150+ papers in these fields. He has been serving as reviewer for the EU Commission (6th and 7th FP), research-support National Agencies (France, Poland, Cyprus, Singapore), and the ERC. Flavio Lombardi is a researcher at the Istituto per le Applicazioni del Calcolo (IAC) of the Italian National Research Council (CNR); he is also Adjunct Professor of Computer Science at the Department of Mathematics of Università di Roma Tre—Roma, Italy; and, a member of the Security and PRivacy INnovation GRoup (SPRINGER) at Roma Tre. He received the Ph.D. in Computer Science from Dipartimento di Informatica of Università degli Studi di Roma “La Sapienza”. His main research interests are in the areas of: security and privacy in the cloud; virtualization security; GPGPU computing; security and privacy for distributed systems. Fabio Martinelli is a senior researcher of Institute of Informatics and Telematics (IIT) of the Italian National Research Council (CNR) where He leads the security project. He is co-author of more than two hundreds of papers on international journals and conference/workshop proceedings. His main research interests involve security and privacy in distributed and mobile systems and foundations of security and trust. Since 2004 He is in the board of directors of the international school on Foundations of Security Analysis and Design (FOSAD). He founded and chaired the WG on Security and Trust management (STM) of the European Research Consortium in Informatics and Mathematics (ERCIM). He is currently chair of the WG 11.14 in secure engineering of the International Federation of Information Processing (IFIP). He usually manages R&D projects on information and communication security and in particular He is currently the Project Coordinator of the EU Network of Excellence NESSoS on the engineering of secure Future Internet services. He is the co-chair of the Italian technological platform in homeland security (SERIT) and he chairs the WG3 on Research and Innovation of the Network and Information Security (NIS) Platform promoted by the European Commission. Daniele Sgandurra holds a Ph.D. in Computer Science from the University of Pisa. He is currently a Research Associate at the Department of Computing, Imperial College London. Formerly, he has worked at IIT-CNR as a PostDoc Researcher. His main research fields include virtualization and cloud security, mobile security, intrusion detection systems, critical infrastructures and risk management, social network security and privacy.
Publisher Copyright:
© 2015 Elsevier B.V. All rights reserved.
PY - 2015/7
Y1 - 2015/7
N2 - The increasing need for performing expensive computations has motivated outsourced computing, as in crowdsourced applications leveraging worker cloud nodes. However, these outsourced computing nodes can potentially misbehave or fail. Exploiting the redundancy of nodes can help guaranteeing correctness and availability of results. This entails that reliable distributed computing can be achieved at the expense of convenience. In this paper, we provide a solution for a generic class of problems that distribute a parallel computation over a set of nodes where trustworthiness of the outsourced computation is important. In particular, we discuss AntiCheetah, an approach modeling the assignment of input elements to cloud nodes as a multi-round system. AntiCheetah is resilient to node cheating, even in scenarios where smart cheaters return the same fake values. To this end, cost-efficient redundancy is used to detect and correct anomalies. Furthermore, we discuss the benefits and pitfalls of the proposed approach over different scenarios, especially with respect to cheaters' behavior. Extensive experimental results are analyzed, showing the effectiveness and viability of our approach.
AB - The increasing need for performing expensive computations has motivated outsourced computing, as in crowdsourced applications leveraging worker cloud nodes. However, these outsourced computing nodes can potentially misbehave or fail. Exploiting the redundancy of nodes can help guaranteeing correctness and availability of results. This entails that reliable distributed computing can be achieved at the expense of convenience. In this paper, we provide a solution for a generic class of problems that distribute a parallel computation over a set of nodes where trustworthiness of the outsourced computation is important. In particular, we discuss AntiCheetah, an approach modeling the assignment of input elements to cloud nodes as a multi-round system. AntiCheetah is resilient to node cheating, even in scenarios where smart cheaters return the same fake values. To this end, cost-efficient redundancy is used to detect and correct anomalies. Furthermore, we discuss the benefits and pitfalls of the proposed approach over different scenarios, especially with respect to cheaters' behavior. Extensive experimental results are analyzed, showing the effectiveness and viability of our approach.
KW - Autonomous cloud computing
KW - Cheaters detection
KW - Trustworthy computation in cloud
UR - http://www.scopus.com/inward/record.url?scp=84924206975&partnerID=8YFLogxK
U2 - 10.1016/j.future.2015.02.004
DO - 10.1016/j.future.2015.02.004
M3 - Article
AN - SCOPUS:84924206975
SN - 0167-739X
VL - 48
SP - 28
EP - 38
JO - Future Generation Computer Systems
JF - Future Generation Computer Systems
ER -