Jul 2026· International Mediterranean Conference on Communications and Networking· pp. 1-6· 0 citations· 14 references
Abstract
Vehicular computation offloading (VCOff) enables resource-constrained vehicles to delegate delay-sensitive tasks to nearby providers. However, it remains vulnerable to strategic malicious nodes that withhold results, or behave intermittently to evade detection. Although reputation values evolve across repeated interactions, long-term security depends on how these signals are governed and enforced at the decision layer. This paper introduces REVS-T, a four-tier governance and tieraware selection mechanism using reputation bands, warningstreak escalation, and pool partitioning. Under persistent attack at 50% adversarial ratio, REVS-T achieves 91.9% task success and 96.7% malicious avoidance with zero false exclusions, outperforming Threshold by 5.5% and Beta by 14.9%. A four-step ablation under shared reputation-update logic shows composite scoring and four-tier governance as the dominant drivers, with ST-conditioned initialization providing phase-shift adaptation and a fairness guarantee no evaluated baseline achieves.
Maritime emergency networks require routing policies that provide timely and secure packet delivery under sparse deployment, mobility-induced topology variation, heterogeneous node ownership, and potential adversarial interference. Existing approaches usually optimize communication efficiency or trust evaluation separately, offering limited support for mission-priority traffic under constrained link resources. This article proposes a layered trust-aware routing framework that couples task-hierarchical service control with security-aware deep reinforcement learning. The method first applies global pre-screening to remove infeasible or low-value relay candidates according to policy constraints, resource quotas, link load, energy, mobility, and geometric progress. It then uses a dynamic weighted fusion DQN to select the next hop from the screened candidates based on behavioral reputation, jurisdictional/policy attributes, geo-situational awareness, and Network-Operational Safety. Priority-aware scheduling, retransmission control, and task-aware reward shaping are further embedded into the learning loop. In the mobility-controlled performance evaluation at a node speed of 20 m/s, the proposed method improves throughput by 18.3% and reduces end-to-end delay by 22.7% compared with classical routing baselines. In the separate security-oriented evaluation, the method maintains a packet delivery ratio above 92.6% under a representative adversarial setting with 15% malicious nodes.
Bo Lin, Lianyou Lai· Journal of Internet Technolo...· 0 citations
Vehicular consumer electronics increasingly support computation-intensive and latency-sensitive services, imposing stringent efficiency, reliability, and security requirements on vehicular edge computing (VEC) systems. In dynamic vehicular environments, inference-based information leakage and anomalous communication behaviors further threaten system performance and data privacy. To address these challenges, this paper proposes a UAV-assisted cooperative VEC architecture that integrates threat-aware task offloading with intelligent spatiotemporal caching across roadside units (RSUs) and UAV edge nodes. A security-aware uplink transmission model is developed to capture potential information leakage risks and abnormal communication patterns, enabling adaptive offloading decisions. We formulate a joint optimization problem to minimize end-to-end task execution delay while improving cache utilization under limited computing and storage resources. To efficiently solve this problem, a Threat-Aware Joint Optimization (TAGO) framework is designed by combining proximal policy optimization for adaptive task offloading and a gradient-based caching update derived from the Frank-Wolfe algorithm to capture spatiotemporal service popularity. Simulation results demonstrate that the proposed approach significantly reduces task delay and improves cache efficiency compared with several baseline strategies, showing its effectiveness for secure and efficient UAV-assisted vehicular consumer electronics systems.
Edge computing and Internet of Things (IoT) have expanded the attack surface of modern networks. Security designs often tradeoff detection quality and privacy: centralized trust creates single points of failure, while distributed approaches may sacrifice accuracy or formal privacy guarantees. This article presents a federated trust modeling framework that integrates multimodal anomaly detection, Byzantine-resilient federated learning with $(\epsilon,\delta)$-differential privacy (DP), and context-aware zero trust architecture decision-making. The three-layer architecture comprises device-level trust learning with enhanced variational autoencoder, Isolation Forest, long short-term memory, and statistical process control modalities; a federated aggregation layer for robust aggregation with DP; and a trust scoring and decision layer that maps evidence to continuous trust and access levels using a subjective logic-inspired formulation. We provide detailed algorithmic implementations with pseudocode for each layer. Comprehensive evaluation demonstrates exceptional performance: high precision with low false positive rate, near-linear scalability achieving high efficiency, high accuracy with precision detecting most of attacks with zero false alarms, and sublinear time complexity. Privacy preservation is maintained through DP guarantees without accuracy degradation. The results support deployability studies for large-scale IoT and Artificial Intelligence of Things settings, with generalization to real telemetry left to future work.
Shengjie Xu, Yi Qian· IEEE Journal of Selected Are...· 0 citations
Payment Channel Networks (PCNs) offer a scalable solution for off-chain cryptocurrency transactions, but suffer from low success rates and security challenges. A key issue lies in the lack of visibility into channel balances during route discovery, which prevents senders from reliably assessing whether a route can support the payment. To address this, we propose a routing protocol that integrates Secure Multiparty Computation (MPC) with a node reputation system. Our method enables senders to privately verify route feasibility before initiating Hash Time-Locked Contracts (HTLCs), reducing transaction failures. The node reputation system identifies and avoids unreliable nodes based on historical behavior, enhancing routing reliability even in adversarial settings. Experimental results on real Lightning Network snapshots across diverse parameter settings demonstrate that our approach substantially outperforms both the baseline shortest-path approach and the routing scheme used in the current Lightning Network implementation.
Cloud environments built on Amazon Web Services face a structural security vulnerability: once a credential passes authentication, the resulting session is often treated as trusted for its entire duration. This assumption fails when credentials are stolen. We introduce the Explainable Adaptive Zero Trust Framework (EAZTF), a cloud-native security layer that continuously reevaluates the legitimacy of API actions throughout a session. EAZTF combines Isolation Forest and XGBoost to evaluate eight CloudTrail and IAM-derived behavioral features in real time and produce a Trust Risk Score (TRS) that determines whether a session continues, requires step-up MFA, or is restricted. Each decision is accompanied by a SHAP or LIME explanation, providing human-readable audit records for security analysis and compliance. The framework is also evaluated against four adversarial evasion strategies: credential theft, behavioral mimicry, API rate evasion, and privilege escalation. Experiments on an 8,500-record synthetic CloudTrail dataset show that Isolation Forest achieves 94.4% precision, 91.2% recall, and an F1 score of 0.928. Across the four adversarial scenarios, the mean detection rate is 91.0%, with behavioral mimicry being the most difficult at 83.9%. SHAP analysis identifies IP reputation, login-time deviation, and API call velocity as the three dominant features. A structured NIST SP 800-207 self-assessment gives EAZTF a mean compliance score of 93%, compared with 38% for a traditional perimeter baseline. Mean time to detect decreases from hours to under one minute. Because the evaluation uses synthetic data, these results should be interpreted as indicative rather than validated production performance.
Om Singh, Yagyaraj Pandey, Nandini Pathak· 0 citations
The shift toward modular microservices has driven the success of serverless Function-as-a-Service (FaaS) as a way to offload infrastructure management. However, meeting the diverse needs of emerging applications—from ultra-low latency control to budget-constrained processing—requires FaaS to transcend centralized clouds and span the edge-cloud continuum. Yet, this introduces two challenges: orchestrating diverse user demands across heterogeneous capabilities and protecting sensitive requests from the underlying infrastructure. We propose a Privacy-Preserving FaaS Marketplace using decentralized orchestration agents. Providers autonomously trade function offers, enabling multi-objective placement that dynamically satisfies strict user QoS constraints. Crucially, Paillier homomorphic encryption blinds function identifiers during resolution to preserve client privacy. Simulations demonstrate our system improves on traditional latency-minimizing FaaS gateways by optimizing placement and proactively shielding clients from SLA violations. Results validate seamless orchestration in the Edge-Cloud continuum while enabling key trade-offs between agent state aggregation, function placement accuracy, and network overhead.
Francesco Tusa, D. Griffin, Tamás Kiss et al.· International Conference on...· 0 citations