Enforcing trust accountability with backward propagation
Enforcing trust accountability with backward propagation
Trust and reputation management underpins reliable interactions in distributed networks, yet existing trust models rely solely on forward propagation of interaction-based trust signals. They lack robust mechanisms to enforce accountability for the propagated trust signals when negative interactions occur. In addition, such models often fail to initialize newly joined nodes with sparse interaction history, leading to the cold-start problem. In this paper, we propose RepuLink, a two-layer reputation model that couples an endorsement network with an interaction feedback network. RepuLink integrates two concurrent backward propagation mechanisms: Backward Endorsement Penalty Propagation (BEPP), which recursively penalizes endorsers of misbehaving nodes, and Backward Endorsement Reward Propagation (BERP), which rewards endorsers of well-performing nodes. Together, RepuLink enforces endorsement accountability and incentivizes positive behaviors, which form a positive interaction feedback loop. The endorsement layer further provides explainable, endorser-weighted trust initialization for newly joined nodes. Experiments on real-world datasets against representative trust propagation baselines demonstrate that RepuLink outperforms across four evaluation metrics in both interaction-only and full two-layer settings, while preserving comparable efficiency.
accountability mechanism, backward propagation, endorsement, incentive mechanism, reputation, trust
5476–5487
Association for Computing Machinery
Wu, Wenbo
73411935-a317-475b-a056-3f8a93e4f18e
Konstantinidis, George
f174fb99-8434-4485-a7e4-bee0fef39b42
9 August 2026
Wu, Wenbo
73411935-a317-475b-a056-3f8a93e4f18e
Konstantinidis, George
f174fb99-8434-4485-a7e4-bee0fef39b42
Wu, Wenbo and Konstantinidis, George
(2026)
Enforcing trust accountability with backward propagation.
In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2.
vol. 2-B,
Association for Computing Machinery.
.
(doi:10.1145/3770855.3817611).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Trust and reputation management underpins reliable interactions in distributed networks, yet existing trust models rely solely on forward propagation of interaction-based trust signals. They lack robust mechanisms to enforce accountability for the propagated trust signals when negative interactions occur. In addition, such models often fail to initialize newly joined nodes with sparse interaction history, leading to the cold-start problem. In this paper, we propose RepuLink, a two-layer reputation model that couples an endorsement network with an interaction feedback network. RepuLink integrates two concurrent backward propagation mechanisms: Backward Endorsement Penalty Propagation (BEPP), which recursively penalizes endorsers of misbehaving nodes, and Backward Endorsement Reward Propagation (BERP), which rewards endorsers of well-performing nodes. Together, RepuLink enforces endorsement accountability and incentivizes positive behaviors, which form a positive interaction feedback loop. The endorsement layer further provides explainable, endorser-weighted trust initialization for newly joined nodes. Experiments on real-world datasets against representative trust propagation baselines demonstrate that RepuLink outperforms across four evaluation metrics in both interaction-only and full two-layer settings, while preserving comparable efficiency.
Text
2606.08851v1
- Version of Record
More information
Accepted/In Press date: 16 May 2026
Published date: 9 August 2026
Additional Information:
Publisher Copyright:
© 2026 Owner/Author.
Venue - Dates:
2026 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '26), Jeju Island, Republic of Korea, Jeju, Korea, Republic of, 2026-08-09 - 2026-08-13
Keywords:
accountability mechanism, backward propagation, endorsement, incentive mechanism, reputation, trust
Identifiers
Local EPrints ID: 513151
URI: https://eprints.soton.ac.uk/id/eprint/513151
ISSN: 2154-817X
PURE UUID: 39b14ba7-16e0-4323-8dc1-ce9e0eac45f3
Catalogue record
Date deposited: 04 Aug 2026 16:57
Last modified: 04 Nov 2026 03:27
Export record
Altmetrics
Contributors
Author:
Wenbo Wu
Author:
George Konstantinidis
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics