Adaptive Traffic Camouflage: Causal and Resource-Aware Defense Against IoT Fingerprinting
A causal IoT traffic-camouflage defense cuts fingerprinting Macro-F1 by up to 43.5% with limited bandwidth cost.
Researchers present Adaptive Traffic Camouflage, a causal controller that estimates IoT traffic-shape leakage without runtime device labels and selects a budget-feasible transform for the next window. Choices include padding, packet splitting, timing changes, composites, or leaving traffic unchanged. On CIC-IoT-2022, IoT Sentinel, and UNSW, the Balanced profile reduced mean Macro-F1 by 13.2-23.3% versus clean traffic, with 4.88-7.47% average bandwidth overhead and at most 0.64 ms added latency. The Privacy profile reached a 28.0-43.5% reduction, but defense-aware training recovered much attacker performance on CIC-IoT-2022 and UNSW.
- Controller picks padding, splitting, timing, or no change per window.
- Balanced profile cuts Macro-F1 13.2-23.3% with under 7.5% bandwidth overhead.
- Privacy profile reduces fingerprinting Macro-F1 by 28.0-43.5%.
- Defense-aware training recovers much attacker accuracy on two datasets.
From the original article
1 min read at arxiv.orgEncryption hides IoT payloads, but traffic shape can still reveal device identity through packet sizes, timing, direction, and packetization. We present Adaptive Traffic Camouflage, a causal, leakage-aware controller that characterizes traffic-shape leakage without runtime device labels and selects a budget-feasible transformation for the next traffic window from previous-window context.
By Daniel Adu Worae · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.