Ubiquitous Computing Environments Provide Rich Behavioral Data

The ubihave project investigates how ubiquitous computing devices can benefit from behavioral models. This research is motivated by the fact that computers permeate our life as everyday companions (smartphones, tablets, life-logging wristbands, smart clothes) and as sensors embedded in the environment (WiFi hotspots, NFC, cameras, depth sensors, eye trackers). These devices provide rich streams of user-specific data, opening new avenues for applications using behavioral models. By exploiting and combining ubiquitous data sources for modeling user behavior, the Human-Computer Interaction community has the unprecedented chance to now realize long held visions of intelligent interfaces, smart devices, and reactive environments which appropriately adapt to individual users and contexts. 

Benefits of Modeling User Behavior

Many current UIs and devices can react to simple sensor properties. However, interfaces and interactions are rarely adapted to the individual user and context, since this requires dedicated inference tools to process uncertain user-specific sensor data. To render user-specific information more accessible and useful to applications and users, this project aims to build and apply models that can describe, analyze and predict user behavior based on data from mobile devices and ubiquitous sensors. Particular application areas that we expect to strongly benefit from such models are usable privacy and security, touch interaction, text input, and context-aware adaptive interfaces. 

Research Questions

This project integrates HCI and user modeling perspectives to address a number of guiding questions: In which applications and contexts can users benefit from behavioral models? How can models improve interactions? Do users notice and like adaptations and do they match their expectations? Which features, models and algorithms are suitable to capture and utilize user behavior? How do we define performance metrics for user actions with behavior-aware interfaces? Which interactions provoke characteristic and consistent behavior? 

Impact

The contribution of the project is threefold. Firstly, we chart a holistic design space to understand and investigate user modeling comprehensively across tasks and beyond the desktop. This reveals future opportunities and a goal unique to this project: we aim to identify common grounds for diverse applications based on the same user representation, leading to efficient data handling across applications. Secondly, we use deployment-based research to identify scenarios in which behavioral biometrics help to optimize, personalize and secure interactions. Examples include novel usable security mechanisms, efficient and usable mobile text entry, activity-aware applications, and novel mobile services that can adapt to user behavior. Thirdly, to allow applications to consider user-specific interaction characteristics and behavior, this project also develops inference tools, which can process uncertain sensor data with respect to the targeted user contexts and goals.

• Go for Gold
  https://www.unibw.de/usable-security-and-privacy/research/datasets/go-for-gold 
• Intentional Behavior Modifications
  https://www.unibw.de/usable-security-and-privacy/research/datasets/intentional-behaviour-modifications 
• How Unique do we move?
  https://www.unibw.de/usable-security-and-privacy/research/datasets/unique-body-moves    

• CHI Course “Introduction to Authentication Using Behavioral Biometrics”
  https://dl.acm.org/doi/abs/10.1145/3544549.3574190 
• VHS Course “Security in Smart Homes”
  https://www.unibw.de/code/news/vhs-workshop-sicherheit-im-smart-home
• Special Issue “Emerging Trends in Usable Security and Privacy”
  https://www.degruyter.com/journal/key/icom/18/3/html?lang=en

• Behavior and Physiology-Aware User Interfaces for Security, Keynote @ACM Augmented Humans 2023, Glasgow, Scotland, 13. March 2023
• Where Ubicomp Meets Usable Security - Novel Security User Interfaces based on User Behavior and Physiology
  Invited Talks at the University of Bremen, 15.05.2023
• Behavioral Security – Challenges and Opportunities of Behavioral Biometrics from an HCI Perspective
  Invited Talk at the Graphics Interfaces 2021 conference, 28.05.2021
• Authentication Beyond Desktop and Smartphone - How Trends in Ubiquitous Computing will Affect User-Centered Security
  Invited Talk at the Usable Security and Privacy Day (USP’20), TU Berlin / Fraunhofer AISEC, 10.01.2020

• Praktikum “Design Sicherer und Benutzbarer Systeme” (UniBW). FT 2019, FT 2020, FT 2021, FT 2022, FT 2023
• Praktikum “Usable Security and Privacy” (HAW München), SoSe 2018, SoSe 2019
• Praktikum “Usable Security and Privacy” (LMU München), SoSe 2020, SoSe 2021, SoSe 2022, SoSe 2023
• Vorlesungen “Benutzbare Sicherheit” (UniBW), FT 2019, FT 2020, FT 2021, FT 2022, FT 2023
• Security and Privacy in the Context of Intelligent User Interfaces
  Invited Lecture in the Intelligent User Interface Course, LMU Munich, WT 2020, WT 2022

Master Theses (2018 - 2022)

• Matthias Geiger (2018) – Behavioral Biometrics in VR
  in collaboration with Dr. Ken Pfeuffer (Bundeswehr University Munich)
• Maria-Lena Bittl (2018) – Investigating User Perceptions of Biometric Wearables
  in collaboration with Prof. Dr. Sven Mayer (LMU Munich)
• Anna Ovsjannikova (2018) – Analyzing the Influence of GUI Elements and Hand Postures on Touch-
  based Behavioral Biometrics
  in collaboration with Prof. Dr. Daniel Buschek (University of Bayreuth)
• Jan Kaiser (2019) – Investigating User behavior in Smart Homes
  in collaboration with Dr. Emanuel von Zezschwitz (Google Inc.)
• Elisaveta Karypidou (2021) – Investigating Human behavior towards Fake News on Social Media

Bachelor Theses (2018 - 2022)

• Matthias Kiermeier (2018) – Explicit behavior Variations for Passwords on Mobile Device
  in collaboration with Daniel Buschek (University of Bayreuth)
• Robin Reuter (2018) – Mobile Emotion Assessment in Real-Time using Facial Expressions
  in collaboration with Thomas Kosch (Humbolt University of Berlin)
• Peter Ehrich (2018) – Analysing User behavior in Problem Solving Tasks Using a Smartwatch
  in collaboration with Daniel Buschek (University of Bayreuth) / Ken Pfeuffer (University of Aarhus)
• Sarah Delgado (2018) – Reauthentication Concepts for Biometric Authentication on Mobile Devices
  in collaboration with Daniel Buschek (University of Bayreuth)
• Felix Kakuschke (2019) – Leveraging the Role of Gaze During Password Verification
• Carolin Schuppe (2019) – Comparing Usability of Different Multi-Factor Authentication Models
• Hatem Abdelmoteleb (2019) – Nudging Mechanisms for Frontal Camera Use on Mobile Devices
  in collaboration with Prof. Dr. Mohamed Khamis (University of Glasgow)
• Hannah Maier (2020) – Empirical Evaluation of Gaze-enhanced Menus in Virtual Reality
  in collaboration with Prof. Ken Pfeuffer (University of Aarhus)
• Ryan Steimer (2020) – Phishing Detection Using Eye Gaze and Mouse Movements
• Mohamed Matnawy (2020) – Exploring the Use of Gaze behavior to Enhance Password Assessments
  in collaboration with the German University in Cairo, Egypt
• David Weyenschops (2021) – Phishing Email Susceptibility Detection from Eye Gaze and Keystroke Bio-
  metrics
• Christoph Patezelt (2022) – Investigating Time of Day & Situational Context on Phishing Vulnerability