In this demo abstract we present a custom-built low-power geo-phone sensor node which features on-device mountaineer classification using a convolutional neural network. The execution of such a processing-heavy algorithm on an embedded platform is enabled by optimizing the memory requirement of the neural network through advanced quantization and pipelining techniques. As a result, real-time classification with low energy consumption can be achieved.

In natural hazard warning systems fast decision making is vital to avoid catastrophes. Decision making at the edge of a wireless sensor network promises fast response times but is limited by the availability of energy, data transfer speed, processing and memory constraints. In this work we present a realization of a wireless sensor network for hazard monitoring based on an array of event-triggered single-channel micro-seismic sensors with advanced signal processing and characterization capabilities based on a novel co-detection technique. On the one hand we leverage an ultra-low power, threshold-triggering circuit paired with on-demand digital signal acquisition capable of extracting relevant information exactly and efficiently at times when it matters most and consequentially not wasting precious resources when nothing can be observed. On the other hand we utilize machine-learning-based classification implemented on low-power, off-the-shelf microcontrollers to avoid false positive warnings and to actively identify humans in hazard zones. The sensors' response time and memory requirement is substantially improved by quantizing and pipelining the inference of a convolutional neural network. In this way, convolutional neural networks that would not run unmodified on a memory constrained device can be executed in real-time and at scale on low-power embedded devices. A field study with our system is running on the rockfall scarp of the Matterhorn Hörnligrat at 3500 m a.s.l. since 08/2018.

Most modern processors use dynamic voltage and frequency scaling (DVFS) for power management. DVFS allows to optimize power consumption by scaling voltage and frequency depending on performance demand. Previous research has indicated that this frequency scaling might pose a security threat in the form of a covert channel, which could leak sensitive information. However, an analysis able to determine whether DVFS is a serious security issue is still missing. In this paper, we conduct a detailed analysis of the threat potential of a DVFS-based covert channel. We investigate two multicore platforms representative of modern laptops and hand-held devices. Furthermore, we develop a channel model to determine an upper bound to the channel capacity, which is in the order of 1 bit per channel use. Last, we perform an experimental analysis using a novel transceiver implementation. The neural network-based receiver yields packet error rates between 1% and 8% at average throughputs of up to 1.83 and 1.20 bps for platforms representative of laptops and hand-held devices, respectively. Considering the well-known small message criterion, our results show that a relevant covert channel can be established by exploiting the behavior of computing systems with DVFS.