Projects | Daniel Adu Worae

Adaptive Traffic Camouflage

Tue, 22 Sep 2026 00:00:00 +0000

Adaptive Traffic Camouflage protects device identity against traffic-based fingerprinting by selecting camouflage actions using observations from previously completed traffic windows. It assesses leakage, identifies resource-feasible actions, and applies guarded action selection under bandwidth and latency constraints. The framework is evaluated across public IoT traffic datasets and multiple attacker adaptation regimes.

NEXUS-MI

Wed, 09 Sep 2026 00:00:00 +0000

NEXUS-MI is a gateway-coordinated federated learning framework for personalized motor-imagery brain-computer interfaces. It supports shared-backbone learning and local classifier-head adaptation while keeping raw EEG and personalized heads local. Its communication policies govern gateway participation, offline buffering, stale updates, and backbone distribution, and are evaluated through public EEG dataset replay.

Revelation

Mon, 13 Oct 2025 00:00:00 +0000

Revelation transforms raw IoT packet captures into structured traffic artifacts, including protocol logs, packet-layer views, flow summaries, anomaly reports, and threat-intelligence context. An agent then supports evidence-grounded question answering over the indexed traffic corpus.

IoT Traffic Camouflage

Sat, 25 Jan 2025 00:00:00 +0000

IoT Traffic Camouflage studies practical traffic obfuscation mechanisms that reduce metadata leakage from encrypted IoT communications. The framework evaluates padding, shifting, fragmentation, constant-size padding, and delay randomization across public IoT datasets.

IoT Shepherd

Mon, 30 Dec 2024 00:00:00 +0000

IoT Shepherd is an agent-orchestrated framework for contextual IoT management and secure ecosystem administration. It connects retrieval-augmented documentation support with transformer-based traffic anomaly detection to generate evidence-grounded operational guidance.