{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/98441"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/98441","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Defending distributed systems against adversarial attacks: consensus, consensus-based learning, and statistical learning","abstract":"A distributed system consists of networked components that interact with each other in order to achieve a common goal. Given the ubiquity of distributed systems and their vulnerability to adversarial attacks, it is crucial to design systems that are provably secured. In this dissertation, we propose and explore the problems of performing consensus, consensus-based learning, and statistical learning in the presence of malicious components. (1) Consensus: In this dissertation, we explore the influence of communication range on the computability of reaching iterative approximate consensus. Particularly, we characterize the tight topological condition on the networks for consensus to be achievable in the presence of Byzantine components. Our results bridge the gap of previous work. (2) Consensus-Based Learning: We propose, to the best of our knowledge, consensus-based Byzantine-tolerant learning problems: Consensus-Based Multi-Agent Optimization and Consensus-Based Distributed Hypothesis Testing. For the former, we characterize the performance degradation, and design efficient algorithms that can achieve the optimal fault-tolerance performance. For the latter, we propose, as far as we know, the first learning algorithm under which the good agents can collaboratively identify the underlying truth. (3) Statistical Learning: Finally, we explore distributed statistical learning, where the distributed system is captured by the server-client model. We develop a distributed machine learning algorithm that is able to (1) tolerate Byzantine failures, (2) accurately learn a highly complex model with low local data volume, and (3) converge exponentially fast using logarithmic communication rounds.","abstract_html":"A distributed system consists of networked components that interact with each other in order to achieve a common goal. Given the ubiquity of distributed systems and their vulnerability to adversarial attacks, it is crucial to design systems that are provably secured. In this dissertation, we propose and explore the problems of performing consensus, consensus-based learning, and statistical learning in the presence of malicious components. (1) Consensus: In this dissertation, we explore the influence of communication range on the computability of reaching iterative approximate consensus. Particularly, we characterize the tight topological condition on the networks for consensus to be achievable in the presence of Byzantine components. Our results bridge the gap of previous work. (2) Consensus-Based Learning: We propose, to the best of our knowledge, consensus-based Byzantine-tolerant learning problems: Consensus-Based Multi-Agent Optimization and Consensus-Based Distributed Hypothesis Testing. For the former, we characterize the performance degradation, and design efficient algorithms that can achieve the optimal fault-tolerance performance. For the latter, we propose, as far as we know, the first learning algorithm under which the good agents can collaboratively identify the underlying truth. (3) Statistical Learning: Finally, we explore distributed statistical learning, where the distributed system is captured by the server-client model. We develop a distributed machine learning algorithm that is able to (1) tolerate Byzantine failures, (2) accurately learn a highly complex model with low local data volume, and (3) converge exponentially fast using logarithmic communication rounds.","abstract_has_math":false,"creators":["Su, Lili"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Vaidya, Nitin H.","Attiya, Hagit","Hajek, Bruce","Srikant, R."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-09-29T17:57:13Z","date_published":"2017-09-29T17:57:13Z","updated_at":"2026-07-22T22:24:35Z","subjects":["Fault-tolerance","Adversaries","Security","Consensus","Optimization","Hypothesis testing","Statistical learning"],"languages":["en"],"rights":["Copyright 2017 Lili Su"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/98441","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Vaidya, Nitin H.","Attiya, Hagit","Hajek, Bruce","Srikant, R."]},{"key":"dc:creator","label":"Author","values":["Su, Lili"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-09-29T17:57:13Z","2017-07-12","2017-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Fault-tolerance","Adversaries","Security","Consensus","Optimization","Hypothesis testing","Statistical learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2017 Lili Su"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/98441"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["A distributed system consists of networked components that interact with each other in order to achieve a common goal. Given the ubiquity of distributed systems and their vulnerability to adversarial attacks, it is crucial to design systems that are provably secured. In this dissertation, we propose and explore the problems of performing consensus, consensus-based learning, and statistical learning in the presence of malicious components. (1) Consensus: In this dissertation, we explore the influence of communication range on the computability of reaching iterative approximate consensus. Particularly, we characterize the tight topological condition on the networks for consensus to be achievable in the presence of Byzantine components. Our results bridge the gap of previous work. (2) Consensus-Based Learning: We propose, to the best of our knowledge, consensus-based Byzantine-tolerant learning problems: Consensus-Based Multi-Agent Optimization and Consensus-Based Distributed Hypothesis Testing. For the former, we characterize the performance degradation, and design efficient algorithms that can achieve the optimal fault-tolerance performance. For the latter, we propose, as far as we know, the first learning algorithm under which the good agents can collaboratively identify the underlying truth. (3) Statistical Learning: Finally, we explore distributed statistical learning, where the distributed system is captured by the server-client model. We develop a distributed machine learning algorithm that is able to (1) tolerate Byzantine failures, (2) accurately learn a highly complex model with low local data volume, and (3) converge exponentially fast using logarithmic communication rounds.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-09-29 without embargo terms","The student, Lili Su, accepted the attached license on 2017-07-11 at 16:07.","The student, Lili Su, submitted this Dissertation for approval on 2017-07-11 at 16:24.","This Dissertation was approved for publication on 2017-07-12 at 15:09.","DSpace SAF Submission Ingestion Package generated from Vireo submission #6232 on 2017-09-29 at 11:25:03","Made available in DSpace on 2017-09-29T17:57:13Z (GMT). No. of bitstreams: 2 SU-DISSERTATION-2017.pdf: 927216 bytes, checksum: 567719f844bd5ad8eae16dd19bda1170 (MD5) LICENSE.txt: 4204 bytes, checksum: 56fcc7dfb144507fbde90eafaaeec27d (MD5) Previous issue date: 2017-07-12"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Defending distributed systems against adversarial attacks: consensus, consensus-based learning, and statistical learning"]}]}],"canonical_facts":{"dc:contributor":["Vaidya, Nitin H.","Attiya, Hagit","Hajek, Bruce","Srikant, R."],"dc:creator":["Su, Lili"],"dc:date":["2017-09-29T17:57:13Z","2017-07-12","2017-08"],"dc:description":["A distributed system consists of networked components that interact with each other in order to achieve a common goal. Given the ubiquity of distributed systems and their vulnerability to adversarial attacks, it is crucial to design systems that are provably secured. In this dissertation, we propose and explore the problems of performing consensus, consensus-based learning, and statistical learning in the presence of malicious components. (1) Consensus: In this dissertation, we explore the influence of communication range on the computability of reaching iterative approximate consensus. Particularly, we characterize the tight topological condition on the networks for consensus to be achievable in the presence of Byzantine components. Our results bridge the gap of previous work. (2) Consensus-Based Learning: We propose, to the best of our knowledge, consensus-based Byzantine-tolerant learning problems: Consensus-Based Multi-Agent Optimization and Consensus-Based Distributed Hypothesis Testing. For the former, we characterize the performance degradation, and design efficient algorithms that can achieve the optimal fault-tolerance performance. For the latter, we propose, as far as we know, the first learning algorithm under which the good agents can collaboratively identify the underlying truth. (3) Statistical Learning: Finally, we explore distributed statistical learning, where the distributed system is captured by the server-client model. We develop a distributed machine learning algorithm that is able to (1) tolerate Byzantine failures, (2) accurately learn a highly complex model with low local data volume, and (3) converge exponentially fast using logarithmic communication rounds.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-09-29 without embargo terms","The student, Lili Su, accepted the attached license on 2017-07-11 at 16:07.","The student, Lili Su, submitted this Dissertation for approval on 2017-07-11 at 16:24.","This Dissertation was approved for publication on 2017-07-12 at 15:09.","DSpace SAF Submission Ingestion Package generated from Vireo submission #6232 on 2017-09-29 at 11:25:03","Made available in DSpace on 2017-09-29T17:57:13Z (GMT). No. of bitstreams: 2 SU-DISSERTATION-2017.pdf: 927216 bytes, checksum: 567719f844bd5ad8eae16dd19bda1170 (MD5) LICENSE.txt: 4204 bytes, checksum: 56fcc7dfb144507fbde90eafaaeec27d (MD5) Previous issue date: 2017-07-12"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/98441"],"dc:language":["en"],"dc:rights":["Copyright 2017 Lili Su"],"dc:subject":["Fault-tolerance","Adversaries","Security","Consensus","Optimization","Hypothesis testing","Statistical learning"],"dc:title":["Defending distributed systems against adversarial attacks: consensus, consensus-based learning, and statistical learning"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:35Z"}