arXiv subjects

Okemawo Obadofin

Publications and source records attributed to Okemawo Obadofin.

3 recordsLinked to original sources

arXiv2026

Surviving the Edge: Federated Learning under Networking and Resource Constraints

Motivated by the growing proliferation of federated learning (FL) in edge environments, we present the first systematic characterization of transport-layer breaking points in FL systems operating under conditions of highly constrained network and compute resources. Using a reproducible testbed with chaos engineering tools, we evaluate Flower under progressively degraded network conditions representative of resource-constrained deployments in Africa and similar environments. Our empirical investigation reveals a fundamental mismatch between FL's burst-idle communication pattern and standard TCP connection management. We identify precise operational boundaries: FL training catastrophically fails at 5-second one-way latency due to TCP handshake timeouts, above 50% packet loss due to buffer exhaustion, and with 90% client dropout rates. Through systematic analysis of connection patterns during training rounds, we demonstrate that FL's periodic model update bursts, separated by extended local training periods, violate the assumptions underlying default TCP configurations. To validate the significance of these findings, we show that adjusting just three TCP connection management parameters can significantly reduce training time under extreme latency, proving that transport-layer awareness is not merely beneficial but essential for FL deployment at the network edge. Our characterization methodology and findings provide practitioners with concrete thresholds for determining when standard FL deployments will fail and when advanced reliability techniques become necessary.

cs.NI↗

arXiv2025

Beyond SSO: Mobile Money Authentication for Inclusive e-Government in Sub-Saharan Africa

The rapid adoption of Mobile Money Services (MMS) in Sub-Saharan Africa (SSA) offers a viable path to improve e-Government service accessibility in the face of persistent low internet penetration. However, existing Mobile Money Authentication (MMA) methods face critical limitations, including susceptibility to SIM swapping, weak session protection, and poor scalability during peak demand. This study introduces a hybrid MMA framework that combines Unstructured Supplementary Service Data (USSD)-based multi-factor authentication with secure session management via cryptographically bound JSON Web Tokens (JWT). Unlike traditional MMA systems that rely solely on SIM-PIN verification or smartphone-dependent biometrics, our design implements a three-factor authentication model; SIM verification, PIN entry, and session token binding, tailored for resource-constrained environments. Simulations and comparative analysis against OAuth-based Single Sign-On (SSO) methods reveal a 45% faster authentication time (8 seconds vs. 12 to 15 seconds), 15% higher success under poor network conditions (95% vs. 80%), and increased resistance to phishing and brute-force attacks. Penetration testing and threat modeling further demonstrate a substantial reduction in vulnerability exposure compared to conventional approaches. The primary contributions of this work are: (1) a hybrid authentication protocol that ensures offline accessibility and secure session continuity; (2) a tailored security framework addressing threats like SIM swapping and social engineering in SSA; and (3) demonstrated scalability for thousands of users with reduced infrastructure overhead. The proposed approach advances secure digital inclusion in SSA and other regions with similar constraints.

cs.CR↗

arXiv2025

Network Hexagons Under Attack: Secure Crowdsourcing of Geo-Referenced Data

A critical requirement for modern-day Intelligent Transportation Systems (ITS) is the ability to collect geo-referenced data from connected vehicles and mobile devices in a safe, secure and anonymous way. The Nexagon protocol, which builds on the IETF Locator/ID Separation Protocol (LISP) and the Hierarchical Hexagonal Clustering (H3) geo-spatial indexing system, offers a promising framework for dynamic, privacy-preserving data aggregation. Seeking to address the critical security and privacy vulnerabilities that persist in its current specification, we apply the STRIDE and LINDDUN threat modelling frameworks and prove among other that the Nexagon protocol is susceptible to user re-identification, session linkage, and sparse-region attacks. To address these challenges, we propose an enhanced security architecture that combines public key infrastructure (PKI) with ephemeral pseudonym certificates. Our solution guarantees user and device anonymity through randomized key rotation and adaptive geospatial resolution, thereby effectively mitigating re-identification and surveillance risks in sparse environments. A prototype implementation over a microservice-based overlay network validates the approach and underscores its readiness for real-world deployment. Our results show that it is possible to achieve the required level of security without increasing latency by more than 25% or reducing the throughput by more than 7%.

cs.CR↗