In this talk, I will talk about challenges and exciting new opportunities at the intersection of AI and Security, how AI and deep learning can enable better security, and how Security can enable better AI. In particular, I will talk about secure deep learning and challenges and approaches to ensure the integrity of decisions made by deep learning. I will also give an overview on challenges and new techniques to enable privacy-preserving machine learning. I will also talk about our recent project on confidentiality-preserving smart contracts and towards democratization of AI. Finally, I will conclude with future directions at the intersection of AI and Security.

In the 19th century the world was revolutionized because we could transform energy into useful work. The 21st century is revolutionized due to our ability to transform information (or data) into useful tools. Driven by Moore's law and the exponential growth of data, artificial intelligence is permeating every aspect of our lives. But intelligence is not for free, it costs energy, and therefore money. Evolution has faced this problem for millions of years and made brains about a 100x more energy efficient than modern hardware (or, as in the case of the sea-squirt, decided that it should eat its brain once is was no longer necessary). I will argue that energy will soon be one of the determining factors in AI. Either companies will find it too expensive to run energy hungry ML tools (such as deep learning) to power their AI engines, or the heat dissipation in edge devices will be too high to be safe. The next battleground in AI might well be a race for the most energy efficient combination of hardware and algorithms.

In this talk I will discuss some ideas that could address this problem. The technical hammer that I will exploit is the perfect …

Language communication plays an important role in human learning and skill acquisition. With the emergence of a new generation of cognitive robots, empowering these physical agents to learn directly from human partners about the world and joint tasks becomes increasingly important. In this talk, I will share some recent work on interactive task learning where humans can teach physical agents new tasks through natural language communication and demonstration. I will give examples of language use in interactive task learning and discuss multiple levels of grounding that are critical in this process. I will demonstrate the importance of common-sense knowledge, particularly the acquisition of very basic physical causality knowledge, in grounding human language to actions not only perceived but also performed by the agent. As humans and agents often have mismatched capabilities and knowledge, I will highlight the role of collaboration in communicative grounding to mediate differences and strive for a common ground of joint representations.

Recent successes in artificial intelligence and machine learning have been largely driven by methods for sophisticated pattern recognition, including deep neural networks and other data-intensive methods. But human intelligence is more than just pattern recognition. And no machine system yet built has anything like the flexible, general-purpose commonsense grasp of the world that we can see in even a one-year-old human infant. I will consider how we might capture the basic learning and thinking abilities humans possess from early childhood, as one route to building more human-like forms of machine learning and thinking.
At the heart of human common sense is our ability to model the physical and social environment around us: to explain and understand what we see, to imagine things we could see but haven’t yet, to solve problems and plan actions to make these things real, and to build new models as we learn more about the world. I will focus on our recent work reverse-engineering these capacities using methods from probabilistic programming, program induction and program synthesis, which together with deep learning methods and video game simulation engines, provide a toolkit for the joint enterprise of modeling human intelligence and making AI systems smarter in more …