Network traffic classification is used to identify the nature of traffic on a network. Entities capable of monitoring net-work traffic use classification for all manner of reasons, including identification of mobile applications being used on the network. It is possible that the usage of encrypted messaging applications by users on these networks can be detected, betraying elements of their privacy.In this paper, we describe a system that leverages campus network resources to generate real-world data alongside a more curated dataset captured from Android application traffic. We also explore the ability of machine learning (ML) models to accurately classify traffic from these encrypted messaging applications. Understanding what is revealed from network data is important given that the use of these applications is meant to maximize privacy in the first place.

Given the growing popularity of voice assistants such as Amazon's Alexa/Echo product, this work investigates a potential privacy concern with this type of product. We collect the encrypted TCP traffic moving from the Echo Dot to the Alexa Voice Service (AVS), and then use machine learning techniques to determine who, of a finite set of speakers, is speaking to the Amazon Alexa/Echo product. We achieve close to 80% speaker identification accuracy with two speakers and approximately 30% speaker identification accuracy with 12 speakers. Both results are statistically significant when compared to random guessing. In this work we discuss the privacy implications of encrypted speaker identification using the Amazon Alexa/Echo product. We also present our speaker identification techniques, as well as an analysis of our results. Since this work investigating privacy concerns is in its initial stages, we also outline potential future work.

Localization is a fundamental problem in wireless sensor networks. In many applications, sensor location information is critical for data processing and understanding. While the global positioning system (GPS) can be used to determine mote locations, the high cost often prohibits the ubiquitous use of GPS for location estimates. The cost of GPS has motivated researchers to develop localization protocols that determine mote locations using existing hardware and wireless measurements. Many of these protocols, however, have trade-offs and only perform well on a subset of networks and network configurations. We have developed a WSN localization algorithm that can be configured to perform well in a wide array of WSN configurations and deployments. We compare our algorithm to two well known and accurate algorithms: MDS-MAP and TSL. Through an extensive and credible analysis, we show that our algorithm, CAIRN, produces low localization error in a variety of network configurations. Additionally, we show how to manipulate algorithm parameters to tailor our algorithm for specific network configurations. Our work contributes an in-network WSN localization algorithm that produces accurate mote location estimates in various network configurations and we show that our algorithm outperforms the best existing protocols available.

Earthen dams are critical components in our world's water resource infrastructure, but many are at or near their intended design life. To improve safety margins and ensure water availability, advanced monitoring techniques are required. The contribution of our work is to enable cost effective geophysical monitoring via the development of a wireless hardware platform for geophysical measurements. Our custom platform, called gsMote, has the following features: high resolution and low noise analog to digital conversion, high data rate persistent on-mote storage, dynamically configurable gain and signal filters, gigabyte scale persistent data storage, powerful inter-mote radio communications, and flexible mote to gateway high speed serial communications. In this paper, we provide the details of (1) our custom wireless geophysical hardware platform and (2) our gsMote testbed site, which is a dam in Golden, CO. Finally, we include how others can obtain our gsMote platform for their geophysical monitoring application.

Participation in elementary school classroom settings is dependent on students' abilities to process questions quickly. Pedagogical studies theorize that some students are able to answer a question before other students are able to process the question, creating a division in classroom participation. This paper presents LEVEL (Listening to Everyone's Voice Enhances Learning), a wireless sensor network application to balance, diversify, and encourage in-class participation. LEVEL offers two operating modes: a centralized interface and a distributed adaptive personal interface. The centralized interface features a traffic light to compel students to wait before responding to a question; we LEVEL the participation in the class by visually informing students when a question can be answered. The distributed interface adaptively sets a participation time delay on a per student basis predicated upon previous participation. LEVEL brings a wireless sensor network application to primary school classrooms. LEVEL connects student learning with technology while providing an enhanced in-class experience for all students.

Abstract We present BoostMAC, a CSMA‐based MAC layer protocol for wireless sensor networks that provides an adjustable interface to achieve ultra‐low power operation. To reach low power operation, we adaptively set two radio parameters. First, BoostMAC implements a preamble sampling scheme that allows a mote to dynamically set the length of its duty cycles. Second, we apply machine learning such that a sender can predict its destination's channel polling time and set each outgoing packet's preamble length accordingly. Our two improvements require no extra communication overhead, and each mote in the network implements simple, local models. Energy conservation is one of the most fundamental problems in sensor networks, and by optimizing low‐level operation at the MAC layer, sensor network applications realize an increase in overall performance. We choose habitat monitoring as a motivating sensor network application because it has unique MAC layer demands, such as fluctuating levels of network traffic. Static configuration at the MAC layer inhibits optimal energy conservation within habitat monitoring applications. We implemented BoostMAC in TinyOS simulator (TOSSIM), and we compare its performance to B‐MAC, a well‐known low power MAC protocol with static behavior. We found that BoostMAC saves energy relative to B‐MAC in bursty networks without affecting latency. Copyright © 2007 John Wiley & Sons, Ltd.