2026-09-18T19:14:58Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/104943 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Koyejo, Sanmi Li, Bo Agarwal, Rishika 2019-08-23T20:05:23Z 2019-08-23T20:05:23Z 2019-04-26 2019-05 Adversarial Machine learning is a field of research lying at the intersection of Machine Learning and Security, which studies vulnerabilities of Machine learning models that make them susceptible to attacks. The attacks are inflicted by carefully designing a perturbed input which appears benign, but fools the models to perform in unexpected ways. To date, most work in adversarial attacks and defenses has been done for classification models. However, generative models are susceptible to attacks as well, and thus warrant attention. We study some attacks for generative models like Autoencoders and Variational Autoencoders. We discuss the relative effectiveness of the attack methods, and explore some simple defense methods against the attacks. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2019-08-22 without embargo terms The student, Rishika Agarwal, accepted the attached license on 2019-04-25 at 16:14. The student, Rishika Agarwal, submitted this Thesis for approval on 2019-04-25 at 16:21. This Thesis was approved for publication on 2019-04-26 at 09:02. DSpace SAF Submission Ingestion Package generated from Vireo submission #13928 on 2019-08-22 at 14:46:53 Made available in DSpace on 2019-08-23T20:05:23Z (GMT). No. of bitstreams: 2 AGARWAL-THESIS-2019.pdf: 68305548 bytes, checksum: c0c006c39aa9b62c43c53d9252567ce0 (MD5) LICENSE.txt: 4212 bytes, checksum: af77392a3689704da513a75d890fffaf (MD5) Previous issue date: 2019-04-26 application/pdf http://hdl.handle.net/2142/104943 en Copyright 2019 Rishika Agarwal Adversarial Machine learning, generative models, attacks, defenses Adversarial attacks and defenses for generative models text text Computer Science Computer Science University of Illinois at Urbana-Champaign Thesis M.S.