{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129993"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129993","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Robust steganography: training and error-correction coding against active wardens","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","abstract_has_math":false,"creators":["Hong, Seunghwan"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Moulin, Pierre"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07-25","date_published":"2025-07-25","updated_at":"2026-07-22T22:25:06Z","subjects":["Steganography","Adversarial Training","Error-correcting Codes","Data Augmentation","Active Warden"],"languages":["en","eng"],"rights":["Copyright 2025 Seunghwan Hong"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129993","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Moulin, Pierre"]},{"key":"dc:creator","label":"Author","values":["Hong, Seunghwan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-07-25","2025-08"]},{"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":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Steganography","Adversarial Training","Error-correcting Codes","Data Augmentation","Active Warden"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Seunghwan Hong"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129993"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","The student, Seunghwan Hong, accepted the attached license on 2025-07-25 at 05:48.","The student, Seunghwan Hong, submitted this Thesis for approval on 2025-07-25 at 06:04.","This Thesis was approved for publication on 2025-07-25 at 09:11.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22735 on 2025-10-20 at 20:15:47","Adversarial training can produce steganographically secure models, but their practical utility is limited by a critical fragility to degradations common in real-world channels. This thesis addresses this gap by framing such degradations as the work of an active warden and develops a methodology to create a robust communication system. The research first quantifies the baseline model’s fragility against a suite of attacks. We then systematically investigate data augmentation strategies, demonstrating that training on simple geometric shifts fails to confer spatial invariance. A novel training approach using interpolation, specifically crop-and-resize augmentation, is then proposed and tested. Finally, to address residual errors, we evaluate a range of Error Correcting Codes (ECCs), from simple repetition codes to advanced LDPC codes, to characterize the channel and achieve reliability. Our findings demonstrate that interpolation-based training successfully instills generalized robustness, significantly reducing bit error rates against attacks that previously caused complete failure. The subsequent analysis of ECCs reveals that the steganographic channel under degradation behaves as a Binary Symmetric Channel with a diffuse error profile. Consequently, simple bit-level codes, like 3-repetition coding, are shown to be significantly more effective than complex, block-based codes like Reed-Solomon. This work presents a complete, two-stage methodology that transforms a fragile, theoretical model into a practical and resilient steganographic system by combining interpolation-based training for robustness with appropriate ECC selection for reliability."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Robust steganography: training and error-correction coding against active wardens"]}]}],"canonical_facts":{"dc:contributor":["Moulin, Pierre"],"dc:creator":["Hong, Seunghwan"],"dc:date":["2025-07-25","2025-08"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","The student, Seunghwan Hong, accepted the attached license on 2025-07-25 at 05:48.","The student, Seunghwan Hong, submitted this Thesis for approval on 2025-07-25 at 06:04.","This Thesis was approved for publication on 2025-07-25 at 09:11.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22735 on 2025-10-20 at 20:15:47","Adversarial training can produce steganographically secure models, but their practical utility is limited by a critical fragility to degradations common in real-world channels. This thesis addresses this gap by framing such degradations as the work of an active warden and develops a methodology to create a robust communication system. The research first quantifies the baseline model’s fragility against a suite of attacks. We then systematically investigate data augmentation strategies, demonstrating that training on simple geometric shifts fails to confer spatial invariance. A novel training approach using interpolation, specifically crop-and-resize augmentation, is then proposed and tested. Finally, to address residual errors, we evaluate a range of Error Correcting Codes (ECCs), from simple repetition codes to advanced LDPC codes, to characterize the channel and achieve reliability. Our findings demonstrate that interpolation-based training successfully instills generalized robustness, significantly reducing bit error rates against attacks that previously caused complete failure. The subsequent analysis of ECCs reveals that the steganographic channel under degradation behaves as a Binary Symmetric Channel with a diffuse error profile. Consequently, simple bit-level codes, like 3-repetition coding, are shown to be significantly more effective than complex, block-based codes like Reed-Solomon. This work presents a complete, two-stage methodology that transforms a fragile, theoretical model into a practical and resilient steganographic system by combining interpolation-based training for robustness with appropriate ECC selection for reliability."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129993"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Seunghwan Hong"],"dc:subject":["Steganography","Adversarial Training","Error-correcting Codes","Data Augmentation","Active Warden"],"dc:title":["Robust steganography: training and error-correction coding against active wardens"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:06Z"}