CORE

Increasingly, decisions and actions affecting people's lives are determined by automated systems processing personal data. Excitement about these systems has been accompanied by serious concerns about their opacity and the threats that they pose to privacy, fairness, and other values. Recognizing these concerns, the investigators seek to make real-world automated decision-making systems accountable for privacy and fairness by enabling them to detect and explain violations of these values. The technical work is informed by, and applied to, online advertising, healthcare, an

When users store their data in the cloud, they take many privacy risks: Will the cloud storage provider allow others to see that data? If the user sets sharing rules for the data, will the cloud storage system follow those rules? Recent news stories of user data exfiltration from cloud storage systems show that users have reason for concern. Encrypting files before storing them in the cloud would provide strong protection, but this approach makes it very difficult for users to share data with others and to change their sharing policies.

Deep learning technologies hold great promise to revolutionize the way people live and work. However, deep learning systems are inherently vulnerable to adversarial inputs, which are maliciously crafted samples to trigger deep neural networks to misbehave, leading to disastrous consequences in security-critical applications. The fundamental challenges of defending against such attacks stem from their adaptive and variable nature: adversarial inputs are tailored to target deep neural networks, while crafting strategies vary greatly with concrete attacks.

The domain name system (DNS) is one of the most critical pieces of Internet infrastructure in use today. It underlies how we name nearly all Internet resources, such as "nsf.gov", and its correct operation is implicitly assumed both by end users and in the design of many important applications such as email and the World Wide Web. Unfortunately, DNS is also abused in a wide variety of ways to support criminal activities such as spam, phishing, fraud, and host compromise.

In online social networks, people and their connections often share personal information, such as demographics, interests, and opinions, and leave traces of their interaction with others and content in the network. Not everyone wants to share personal information; however, people's attributes are correlated with each other among themselves, with attributes of nearby people in the network, and between a person's accounts on different networks. These correlations create risks around inferring attributes people would rather keep private.