Grant Year: 2019

January 14, 2020

Secure Machine Learning

We will study how to harden machine learning classifiers against adversarial attack. We will explore general mechanisms for making deep-learning classifiers more robust against attack, with a special focus on security for autonomous vehicles. Current schemes fail badly in the presence of an attacker who is trying to fool or…

January 14, 2020

Cybersecurity Toolkits for/of the Future: A Human-Centered Computing and Design Research Approach

The cybersecurity toolkit—collections of digital tools, tutorials, tips, best practices, and other recommendations—has emerged as a popular approach for preventing and addressing cybersecurity threats and attacks. Often these toolkits are oriented toward vulnerable populations who have unique and pressing needs related to cybersecurity but may not have access to the…

January 14, 2020

Using Multidisciplinary Design to Improve AI/ML Cybersecurity Scenarios

The overarching research question guiding this project is: How can multidisciplinary design methods, perspectives, and forms be applied to improve existing artificial intelligence (AI) cybersecurity scenarios, predictions, and extrapolations produced by researchers, market analysts, government organizations, and industry experts? This research will begin by collecting and carefully reviewing and organizing…

January 14, 2020

The Cybersecurity of “Smart” Infrastructure Systems

Urban infrastructure such as water and sanitation systems, subways, power grids, and flood defense systems are crucial for social and economic life yet are vulnerable to natural hazards that could disrupt services, such as earthquakes or floods. New sensor systems can potentially provide early warnings of problems, and thus help…

January 14, 2020

Privacy-preserving and Decentralized Federated Learning

Machine learning technology is developing rapidly and has been continuously changing our daily life. However, a major limiting factor that hinders many machine learning tasks is the need of huge and diverse training data. Crowdsourcing has been shown effective to collect data labels with a centralized server. The emergence of…

January 14, 2020

Towards Efficient Data Economics: Decentralized Data Marketplace and Smart Pricing Models

Advances in machine learning and artificial intelligence have demonstrated enormous potential for building intelligent systems and growing knowledge bases. However, the current data marketplaces are not efficient enough to facilitate long-term technological and economic advancements. An efficient data market would allow participants to strategically sell or purchase data and get…

January 14, 2020

Privacy for Always-Listening Devices

Microphone-equipped Internet of Things devices, and smart voice assistants specifically, offer the promise of great convenience, yet pose grave privacy challenges. The aim of our research is to understand the privacy implications of voice as a sensitive data source and develop techniques to help users protect their privacy from these…

January 14, 2020

Hackers vs. Testers: Understanding Software Vulnerability Discovery Processes

Security vulnerabilities pose a grave danger to the integrity of any system because they can undermine almost any protection mechanism or safeguard. As such, finding vulnerabilities before the software gets deployed is a critical task in any current software development cycle. A vital tool has recently emerged in the arsenal…

January 14, 2020

Engaging Expert Stakeholders about the Future of Menstrual Biosensing Technology

Networked sensor technologies are increasingly present in daily life. While promising improved health and efficiency, they also introduce far-reaching issues around cybersecurity, privacy, autonomy, and consent that can be difficult to predict or resist. This project will examine menstrual tracking technologies as a case for understanding the current and near-future…

January 14, 2020

Factors Affecting Trust Among Vulnerable Populations

This project aims to understand the trust dynamics and the factors affecting trust for vulnerable populations like human rights defenders, activists, and journalists who document and upload sensitive media, as well as people who receive this media in order to use it as evidence. The researchers will work to understand…