Dans les systèmes de réputation, il a été observé, qu’afin d’éviter des évaluations vengeresses, les témoignages étaient majoritairement positifs, réduisant par là-même l’efficacité du système. Pour inciter les agents à diffuser tous leurs témoignages, les solutions classiques proposent d’anonymiser les témoignages. Dans la littérature, de nombreux travaux ont étudé des approches cryptographiques pour s’assurer à la fois de l’anonymat et de la non-répudiation des témoignages. Toutefois, ceci ne permet de garantir leur confidentialité en raison des corrélations entre transactions et diffusion d’un nouveau témoignage. Dans cet article, nous proposons d’étudier la faisabilité d’une autre approche dans laquelle les témoignages sont bruités et soumis à des délais de diffusion. Des résultats d’expérimentation mettent en lumière l’effet de ces perturbations sur les systèmes de réputation BetaReputation et EigenTrust.
On reputation systems, it has been observed that testimonies are mostly positive in order to avoid vengeful evaluations. Such behaviour reduces the effectiveness of the system. In order to incite agents to publish all their testimonies, classic solutions consist in anonymizing them. In the literature, many works have proposed cryptographic approaches to ensure both anonymity and non-repudiation of testimonies. However, due to correlations between transactions and dissemination of new testimonies, it does not guarantee confidentiality. In this article, we propose to study the feasibility of another approach in which a noise is applied on testimonies and those latter are subject to delays of diffusion. Experimental results highlight the effect of these disturbances on the BetaReputation and EigenTrust reputation systems.
Révisé le :
Accepté le :
Publié le :
Keywords: Multi-agent systems, Trust and reputation systems, Confidentiality
CC-BY 4.0
@article{ROIA_2022__3_5-6_671_0,
author = {Gr\'egory Bonnet and Laurent Vercouter and Damien Lelerre},
title = {Confidentialit\'e dans les syst\`emes de r\'eputation},
journal = {Revue Ouverte d'Intelligence Artificielle},
pages = {671--689},
publisher = {Association pour la diffusion de la recherche francophone en intelligence artificielle},
volume = {3},
number = {5-6},
year = {2022},
doi = {10.5802/roia.47},
language = {fr},
url = {https://roia.centre-mersenne.org/articles/10.5802/roia.47/}
}
TY - JOUR AU - Grégory Bonnet AU - Laurent Vercouter AU - Damien Lelerre TI - Confidentialité dans les systèmes de réputation JO - Revue Ouverte d'Intelligence Artificielle PY - 2022 SP - 671 EP - 689 VL - 3 IS - 5-6 PB - Association pour la diffusion de la recherche francophone en intelligence artificielle UR - https://roia.centre-mersenne.org/articles/10.5802/roia.47/ DO - 10.5802/roia.47 LA - fr ID - ROIA_2022__3_5-6_671_0 ER -
%0 Journal Article %A Grégory Bonnet %A Laurent Vercouter %A Damien Lelerre %T Confidentialité dans les systèmes de réputation %J Revue Ouverte d'Intelligence Artificielle %D 2022 %P 671-689 %V 3 %N 5-6 %I Association pour la diffusion de la recherche francophone en intelligence artificielle %U https://roia.centre-mersenne.org/articles/10.5802/roia.47/ %R 10.5802/roia.47 %G fr %F ROIA_2022__3_5-6_671_0
Grégory Bonnet; Laurent Vercouter; Damien Lelerre. Confidentialité dans les systèmes de réputation. Revue Ouverte d'Intelligence Artificielle, Volume 3 (2022) no. 5-6, pp. 671-689. doi : 10.5802/roia.47. https://roia.centre-mersenne.org/articles/10.5802/roia.47/
[1] A General Survey of Privacy-Preserving Data Mining Models and Algorithms, Privacy-Preserving Data Mining, Springer, 2008, pp. 11-52 | DOI
[2] , International Symposium on Privacy Enhancing Technologies Symposium (2008), pp. 202-218 | DOI
[3] Fuzzy Techniques for Trust and Reputation Management in Anonymous Peer-to-Peer Systems, Journal of the American Society for Information Science and Technology, Volume 57 (2006) no. 4, pp. 528-537 | DOI
[4] A Survey of Trust in Computer Science and the Semantic Web, Web Semantics : Science, Services and Agents on the World Wide Web, Volume 5 (2007) no. 2, pp. 58-71 | DOI
[5] Finite-Time Analysis of the Multi-Armed Bandit Problem, Machine Learning, Volume 47 (2002) no. 2–3, pp. 235-256 | DOI | Zbl
[6] , 3rd International Conference on Fuzzy Sets and Fuzzy Systems, Volume 200 (2002), pp. 147-153
[7] , ACM SIGCOMM Workshop on Economics of Peer-to-peer Systems (2005), pp. 128-132 | DOI
[8] , 33rd International Colloquium on Automata, Languages and Programming (2006), pp. 1-12 | DOI | MR | Zbl
[9] Trust and Reputation Models for Multi-Agent Systems, ACM Computing Surveys, Volume 48 (2015) no. 2, 27, 42 pages | DOI
[10] A Survey of Trust in Internet Applications, Communications Surveys & Tutorials, IEEE, Volume 3 (2000) no. 4, pp. 2-16 | DOI
[11] Preserving Privacy of Feedback Providers in Decentralized Reputation Systems, Computers and Security, Volume 31 (2012) no. 7, pp. 816-826 | DOI
[12] , 37th Annual IEEE Conference on Local Computer Networks (2012), pp. 10-18 | DOI
[13] , 15th Bled Conference on Electronic Commerce (2002), pp. 324-337
[14] A Survey of Trust and Reputation Systems for Online Service Provision, Decision support systems, Volume 43 (2007) no. 2, pp. 618-644 | DOI
[15] , 12th International Conference on World Wide Web (2003), pp. 640-651 | DOI
[16] A New Measure of Rank Correlation, Biometrika, Volume 30 (1938), pp. 81-89 | DOI
[17] Multiplicative Noise for Masking Continuous Data (2003) (Technical report)
[18] The Retaliatory Feedback Problem : Evidence from eBay and a Proposed Solution, Information Systems Research Methods, Epistemology, and Applications (2009), pp. 342-349 | DOI
[19] Rateweb : Reputation Assessment for Trust Establishment Among Web Services, International Journal on Very Large Data Bases, Volume 18 (2009) no. 4, pp. 885-911 | DOI
[20] Taxonomy of Trust : Categorizing P2P Reputation Systems, Computer Networks, Volume 50 (2006) no. 4, pp. 472-484 | DOI | Zbl
[21] Utilizing Noise Addition for Data Privacy, an Overview, 11th International Conference on Information and Knowledge Engineering (2012), pp. 65-71 | DOI
[22] , 32nd International Conference on Computer Communications (2013), pp. 2517-2525 | DOI
[23] The PageRank Citation Ranking : Bringing Order to the Web (1999) (Technical report)
[24] Computational Trust and Reputation Models for Open Multi-Agent Systems : A Review, Artificial Intelligence Revue, Volume 40 (2013), pp. 1-25 | DOI
[25] Statistical Disclosure Limitation, Journal of Official Statistics, Volume 9 (1993) no. 2, pp. 461-468
[26] Repage : Reputation and Image Among Limited Autonomous Partners, Journal of Artificial Societies and Social Simulation, Volume 9 (2006) no. 2, p. 3
[27] Review on Computational Trust and Reputation Models, Artificial Intelligence Review, Volume 24 (2005) no. 1, pp. 33-60 | DOI | Zbl
[28] , International Conference on Peer-to-Peer Computing (2003), pp. 142-149 | DOI
[29] , 13th International Conference on Practical Applications of Agents and Multi-Agent Systems (2014), pp. 279-290 | DOI
[30] A Survey of Multi-Agent Trust Management Systems, IEEE Access, Volume 1 (2013), pp. 35-50 | DOI
[31] Powertrust : A Robust and Scalable Reputation System for Trusted Peer-to-Peer Computing, IEEE Transactions on Parallel and Distributed Systems, Volume 18 (2007) no. 4, pp. 460-473 | DOI
Cité par Sources :