A Reputation-Aware Adaptive Incentive Mechanism for Federated Learning-Based Smart Transportation

Abstract

Highlights: The proposed framework integrates three key innovations: a multi-dimensional reputation evaluation system for reliable client assessment, a dynamic incentive control module that adaptively tunes reward weights in real time to ensure fairness and sustained convergence, and a penalty-based mechanism leveraging anomaly detection to isolate and discourage untrustworthy participants. What are the main findings? A multi-dimensional reputation evaluation system was developed for reliable client selection and incentivization. Elimination of malicious clients and penalization with a two-stage mechanism. What are the implications of the main findings? Legitimate clients are selected with a reputation score is greater than or equal to 0.6 and incentivized through adaptive rewards. Malicious clients are penalized using reputation slashing and suspended from participating in federated learning rounds. Federated learning (FL) has emerged as a promising paradigm for privacy-preserving distributed intelligence in modern urban transportation systems, where vehicles collaboratively train global models without sharing raw data. However, the dynamic nature of vehicular environments introduces critical challenges, including unstable participation, data heterogeneity, and the potential for malicious behavior. Conventional FL frameworks lack effective trust management and adaptive incentive mechanisms capable of maintaining fairness and reliability under these fluctuating conditions. This paper presents a reputation-aware federated learning framework that integrates multi-dimensional reputation evaluation, dynamic incentive control, and malicious client detection through an adaptive feedback mechanism. Each vehicular client is assessed based on data quality, stability, and behavioral consistency, producing a reputation score that directly influences client selection and reward allocation. The proposed feedback controller self-tunes the incentive weights in real time, ensuring equitable participation and sustained convergence performance. In parallel, a penalty module leverages statistical anomaly detection to identify, isolate, and penalize untrustworthy clients without compromising benign contributors. Extensive simulations conducted on real-world datasets demonstrate that the proposed framework achieves higher model accuracy and greater robustness against poisoning and gradient manipulation attacks compared to existing baseline methods. The results confirm the potential of our trust-regulated incentive mechanism to enable reliable federated learning in smart cities transportation systems.