{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/122911"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/122911","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"On practical robustness of machine learning systems","abstract":"We consider the importance of robustness in evaluating machine learning systems, an in particular systems involving deep learning. We consider these systems' vulnerability to adversarial examples--subtle, crafted perturbations to inputs which induce large change in output. We show that these adversarial examples are not only theoretical concern, by desigining the first 3D adversarial objects, and by demonstrating that these examples can be constructed even when malicious actors have little power. We suggest a potential avenue for building robust deep learning models by leveraging generative models.","abstract_html":"We consider the importance of robustness in evaluating machine learning systems, an in particular systems involving deep learning. We consider these systems' vulnerability to adversarial examples--subtle, crafted perturbations to inputs which induce large change in output. We show that these adversarial examples are not only theoretical concern, by desigining the first 3D adversarial objects, and by demonstrating that these examples can be constructed even when malicious actors have little power. We suggest a potential avenue for building robust deep learning models by leveraging generative models.","abstract_has_math":false,"creators":["Ilyas, Andrew."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Constantinos Daskalakis."],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018","date_published":"2018","updated_at":"2026-07-22T22:21:55Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/122911","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Constantinos Daskalakis."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Ilyas, Andrew."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2019-11-12T18:13:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2019-11-12T18:13:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2018"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/122911"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 71-79)."]},{"key":"dc:description.abstract","label":"Abstract","values":["We consider the importance of robustness in evaluating machine learning systems, an in particular systems involving deep learning. We consider these systems' vulnerability to adversarial examples--subtle, crafted perturbations to inputs which induce large change in output. We show that these adversarial examples are not only theoretical concern, by desigining the first 3D adversarial objects, and by demonstrating that these examples can be constructed even when malicious actors have little power. We suggest a potential avenue for building robust deep learning models by leveraging generative models."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M. Eng."]},{"key":"dc:title","label":"Title","values":["On practical robustness of machine learning systems"]}]}],"canonical_facts":{"dc:contributor.advisor":["Constantinos Daskalakis."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Ilyas, Andrew."],"dc:date.accessioned":["2019-11-12T18:13:06Z"],"dc:date.available":["2019-11-12T18:13:06Z"],"dc:date.issued":["2018"],"dc:description":["This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 71-79)."],"dc:description.abstract":["We consider the importance of robustness in evaluating machine learning systems, an in particular systems involving deep learning. We consider these systems' vulnerability to adversarial examples--subtle, crafted perturbations to inputs which induce large change in output. We show that these adversarial examples are not only theoretical concern, by desigining the first 3D adversarial objects, and by demonstrating that these examples can be constructed even when malicious actors have little power. We suggest a potential avenue for building robust deep learning models by leveraging generative models."],"dc:description.degree":["M. Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/122911"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["On practical robustness of machine learning systems"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:55Z"}