False-Name-Proofness in Social Networks

Abstract

In mechanism design, the goal is to create rules for making a decision based on the preferences of multiple parties (agents), while taking into account that agents may behave strategically. An emerging phenomenon is to run such mechanisms on a social network; for example, Facebook recently allowed its users to vote on its future terms of use. One significant complication for such mechanisms is that it may be possible for a user to participate multiple times by creating multiple identities. Prior work has investigated the design of false-name-proof mechanisms, which guarantee that there is no incentive to use additional identifiers. Arguably, this work has produced mostly negative results. In this paper, we show that it is in fact possible to create good mechanisms that are robust to false-name-manipulation, by taking the social network structure into account. The basic idea is to exclude agents that are separated from trusted nodes by small vertex cuts. We provide key results on the correctness, optimality, and computational tractability of this approach.

Personalised rating

“…Lobbying and bribery are also established concepts in computational social choice, with their computational complexity being analysed extensively in multiple recent papers (Faliszewski et al, 2009;Baumeister et al, 2011;Bredereck et al, 2014Bredereck et al, , 2016. Although our focus is manipulation by incentives, there are a number of relevant approaches that have close connections to our work, notably the work of Conitzer et al (2010), Waggoner et al (2012), Todo and Conitzer (2013) and Brill et al (2016), which study the effect of adding fake profiles to a social network, a closely related problem to bribery. The importance of this line of research is to demonstrate the role of the graph structure in resisting manipulation, with applications to opinion spreading Alon et al (2015) and community detection Todo and Conitzer (2013).…”

Un protocole fondé sur des dilemmes pour se prémunir des collusions dans les systèmes de réputation

“…Une deuxième classe d'approches consiste à détecter les coalitions malveillantes à l'intérieur du graphe de confiance en considérant que les interactions observées structurent un réseau social [22]. Il est alors fait l'hypothèse que les agents malveillants présentent soit un taux de clusterisation très élevé et peu de liens avec les agents honnêtes [9,24], soit des identifiants similaires [8]. Ces approches utilisent alors des techniques de clustering provenant du domaine de l'analyse de graphes ou de la découverte de liens pour séparer les agents honnêtes des agents malveillants.…”

Mechanism Design for Time Critical and Cost Critical Task Execution via Crowdsourcing

“…In all multi-level marketing mechanisms, the revenue is generated endogenously by the participating nodes, and a fraction of the revenue is redistributed over the referrers. On slightly different kind of tasks, Conitzer et al [2] proposes mechanisms that are robust to false-name manipulation for applications such as facebook inviting its users to vote on its future terms of use. Further, Yu et al [11] proposes a protocol to limit corruptive influence of sybil attacks in P2P networks by exploiting insights from social networks.…”

“…An example of such applications include the DARPA Red Balloon Challenge [3], DARPA CLIQR quest [4], query incentive networks [8], and multi-level marketing [6]. The success of such crowdsourcing applications depends on providing appropriate incentives to individuals for both (1) executing the task by themselves and/or (2) recruiting other individuals. Designing a proper incentive scheme (crowdsourcing mechanism) is crucial to the success of any such crowdsourcing based application.…”