Neil Klingensmith

Maddie Juarez, Abha Rai, Kristen E. Ravi et al.

Low-income individuals can face multiple challenges in their ability to seek employment. Barriers to employment often include limited access to digital literacy resources, training, interview preparation and resume feedback. Prior work has largely focused on targeted social service or healthcare applications that address needs individually, with little emphasis on conversational AI-driven systems that integrate multiple localized digital resources to provide comprehensive support. This work presents HeyFriend Helper, a web-based platform designed to support low-income residents in Chicago through an interactive conversational assistant that provides personalized support and guidance. HeyFriend Helper integrates multiple tools, including resume building and feedback, interview practice, mindfulness and well-being resources, employment trend and career outcome information, language learning support, and location-based access to community services. This work represents an interdisciplinary collaboration between social work, computer science, and engineering that addresses the multifaceted needs of low-income individuals. The findings demonstrate the importance of career-readiness tools and conversational user interface (CUIs) in providing holistic support.

Jack West, Kyuin Lee, Suman Banerjee et al.

Context-based authentication is a method for transparently validating another device's legitimacy to join a network based on location. Devices can pair with one another by continuously harvesting environmental noise to generate a random key with no user involvement. However, there are gaps in our understanding of the theoretical limitations of environmental noise harvesting, making it difficult for researchers to build efficient algorithms for sampling environmental noise and distilling keys from that noise. This work explores the information-theoretic capacity of context-based authentication mechanisms to generate random bit strings from environmental noise sources with known properties. Using only mild assumptions about the source process's characteristics, we demonstrate that commonly-used bit extraction algorithms extract only about 10% of the available randomness from a source noise process. We present an efficient algorithm to improve the quality of keys generated by context-based methods and evaluate it on real key extraction hardware. Moonshine is a randomness distiller which is more efficient at extracting bits from an environmental entropy source than existing methods. Our techniques nearly double the quality of keys as measured by the NIST test suite, producing keys that can be used in real-world authentication scenarios.

Jack West, Tien VoNguyen, Isaac Ahlgren et al.

We present VoltKey, a method that transparently generates secret keys for colocated devices, leveraging spatiotemporally unique noise contexts observed in commercial power line infrastructure. VoltKey extracts randomness from power line noise and securely converts it into an authentication token. Nearby devices which observe the same noise patterns on the powerline generate identical keys. The unique noise pattern observed only by trusted devices connected to a local power line prevents malicious devices without physical access from obtaining unauthorized access to the network. VoltKey is implemented inside of a standard USB power supply as a platform-agnostic bolt-on addition to any IoT or mobile device or any wireless access point that is connected to the power outlet.