• Publications
  • Influence
A Learning and Masking Approach to Secure Learning
TLDR
A new perspective on the problem of adversarial example generation is introduced by first defining robustness of a classifier to adversarial exploitation, and it is shown that the dual approach of the attack learning problem can be used as a defensive technique that is effective against high perturbation attacks.
MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks
TLDR
A fine-grained dataset of collaborative tasks performed by pairs of human subjects in the 3D virtual blocks world of Minecraft is introduced to enable theory of mind modeling in situated interactions.
Using Sociolinguistic Variables to Reveal Changing Attitudes Towards Sexuality and Gender
TLDR
It is demonstrated that attitudes are changing but that these changes are driven by specific demographics within the United States, and it is shown that passages of Marriage Equality Acts in different states are drivers of linguistic change.