PROTECTION OF THE WIRELESS-NETWORK REPUTATION MECHANISM AGAINST ERRONEOUS UPDATES IN THE PRESENCE OF COMPROMISED NODES USING A TYPED k-OUT-OF-N RULE

Abstract

In wireless networks, node reputation is often updated by comparing a local report with the global fusion decision. Under incomplete coverage or in the presence of compromised sources, this decision may not provide a reliable reference, and a correct report from an honest node may therefore receive a negative update. This paper considers a typed representation of the k-out-of-N outcome intended to reduce such false penalties. The underlying binary decision remains unchanged, while the fusion outcome is additionally classified as a single quorum, double quorum, unreached quorum, insufficient coverage, or no-data state. Reputation is updated only in the single-quorum H1 or H0 states. Implementation correctness was verified by exhaustive enumeration of 15,309 configuration–quota pairs. Classical updating, coverage filtering, a two-sided quorum rule, Bayesian variants, and beta reputation with forgetting were compared experimentally. The base scenario used N=7, k=4, two compromised nodes, and a prior probability P(H1)=0.5. At an abstention probability of 0.5, classical updating produced about 34% unjust penalties of honest nodes, coverage filtering about 28%, whereas typed updating reduced this value to 1.9%. The mean trust difference between honest and compromised nodes was about 0.59. Ablation analysis showed that for k=4 the same result is reproduced by a simpler two-sided quorum rule, while for k=3 the full typology provides a small additional gain. The results indicate that accounting for the structure of the global decision can reduce false penalties of honest nodes without changing the underlying k-out-of-N rule. In practical use, this prevents an insufficiently supported global decision from being unconditionally used as a reference for reputation updates.