Show simple item record

dc.contributor.advisorChau, Duen Horng
dc.contributor.advisorBalcan, Maria-Florina
dc.contributor.authorChen, Shang-Tse
dc.date.accessioned2020-01-14T14:46:15Z
dc.date.available2020-01-14T14:46:15Z
dc.date.created2019-12
dc.date.issued2019-09-20
dc.date.submittedDecember 2019
dc.identifier.urihttp://hdl.handle.net/1853/62296
dc.description.abstractWhile Artificial Intelligence (AI) has tremendous potential as a defense against real-world cybersecurity threats, understanding the capabilities and robustness of AI remains a fundamental challenge. This dissertation tackles problems essential to successful deployment of AI in security settings and is comprised of the following three interrelated research thrusts. (1) Adversarial Attack and Defense of Deep Neural Networks: We discover vulnerabilities of deep neural networks in real-world settings and the countermeasures to mitigate the threat. We develop ShapeShifter, the first targeted physical adversarial attack that fools state-of-the-art object detectors. For defenses, we develop SHIELD, an efficient defense leveraging stochastic image compression, and UnMask, a knowledge-based adversarial detection and defense framework. (2) Theoretically Principled Defense via Game Theory and ML: We develop new theories that guide defense resources allocation to guard against unexpected attacks and catastrophic events, using a novel online decision-making framework that compels players to employ ``diversified'' mixed strategies. Furthermore, by leveraging the deep connection between game theory and boosting, we develop a communication-efficient distributed boosting algorithm with strong theoretical guarantees in the agnostic learning setting. (3) Using AI to Protect Enterprise and Society: We show how AI can be used in real enterprise environment with a novel framework called Virtual Product that predicts potential enterprise cyber threats. Beyond cybersecurity, we also develop the Firebird framework to help municipal fire departments prioritize fire inspections. Our work has made multiple important contributions to both theory and practice: our distributed boosting algorithm solved an open problem of distributed learning; ShaperShifter motivated a new DARPA program (GARD); Virtual Product led to two patents; and Firebird was highlighted by National Fire Protection Association as a best practice for using data to inform fire inspections.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectSecurity
dc.subjectCybersecurity
dc.subjectMachine learning
dc.subjectArtificial Intelligence
dc.subjectAdversarial machine learning
dc.subjectGame theory
dc.subjectBoosting
dc.subjectFire risk
dc.titleAI-infused security: Robust defense by bridging theory and practice
dc.typeDissertation
dc.description.degreePh.D.
dc.contributor.departmentComputational Science and Engineering
thesis.degree.levelDoctoral
dc.contributor.committeeMemberLee, Wenke
dc.contributor.committeeMemberSong, Le
dc.contributor.committeeMemberRoundy, Kevin A.
dc.contributor.committeeMemberCornelius, Cory
dc.date.updated2020-01-14T14:46:15Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record