Nathaniel Fruchter

Leilani H. Gilpin, Cecilia Testart, Nathaniel Fruchter et al.

There is a disconnect between explanatory artificial intelligence (XAI) methods and the types of explanations that are useful for and demanded by society (policy makers, government officials, etc.) Questions that experts in artificial intelligence (AI) ask opaque systems provide inside explanations, focused on debugging, reliability, and validation. These are different from those that society will ask of these systems to build trust and confidence in their decisions. Although explanatory AI systems can answer many questions that experts desire, they often don't explain why they made decisions in a way that is precise (true to the model) and understandable to humans. These outside explanations can be used to build trust, comply with regulatory and policy changes, and act as external validation. In this paper, we focus on XAI methods for deep neural networks (DNNs) because of DNNs' use in decision-making and inherent opacity. We explore the types of questions that explanatory DNN systems can answer and discuss challenges in building explanatory systems that provide outside explanations for societal requirements and benefit.

Nathaniel Fruchter, Hsin Miao, Scott Stevenson et al.

Different countries have different privacy regulatory models. These models impact the perspectives and laws surrounding internet privacy. However, little is known about how effective the regulatory models are when it comes to limiting online tracking and advertising activity. In this paper, we propose a method for investigating tracking behavior by analyzing cookies and HTTP requests from browsing sessions originating in different countries. We collect browsing data from visits to top websites in various countries that utilize different regulatory models. We found that there are significant differences in tracking activity between different countries using several metrics. We also suggest various ways to extend this study which may yield a more complete representation of tracking from a global perspective.