{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/33888"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/33888","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Robust and Fragile Watermarking for Ownership and Integrity Verification of Tabular Data","abstract":"Tabular data are widely shared for machine learning and data analytics. Once released, their owners need to verify ownership of reused data and verify integrity after unauthorized tampering. This thesis develops three watermarking methods for different verification objectives. PKF is a robust watermarking method for ownership verification of tabular data used to train machine learning models. Without relying on primary keys, which adversaries can modify or remove without degrading utility, PKF maps numerical attributes to a discrete-time signal, embeds a sinusoidal watermark, and detects its spectral evidence. Its analysis bounds the attack-induced perturbation under which detection succeeds with high probability. Experiments on two datasets show superior robustness over six baselines under six watermark-removal attacks. RaMark is a robust watermarking method for ownership verification of tabular data generated by generative models. It introduces radioactivity, the property that a watermark remains detectable under a retraining attack, in which a generative model is trained on watermarked data and used to generate new tuples. RaMark embeds a sinusoidal dependency into the data distribution and detects it through spectral analysis. The analysis shows that when regenerated and watermarked data distributions remain close in Wasserstein-1 distance, their spectral powers remain close with high probability. Experiments on two datasets show stronger robustness than seven baselines under retraining attacks. LoMark is a fragile watermarking method for integrity verification of relational databases under sparse tampering. It uses primary key set reconciliation to localize inserted and deleted tuples and group testing to localize value-modified tuples. Theoretical guarantees characterize when localization succeeds with high probability and guide parameter selection under a verification metadata budget. Experiments on four datasets against eight baselines show accurate tuple-level localization using verification metadata amounting to 1% of the database size. Overall, this thesis provides watermarking methods for ownership and integrity verification of released tabular data.","abstract_html":"Tabular data are widely shared for machine learning and data analytics. Once released, their owners need to verify ownership of reused data and verify integrity after unauthorized tampering. This thesis develops three watermarking methods for different verification objectives. PKF is a robust watermarking method for ownership verification of tabular data used to train machine learning models. Without relying on primary keys, which adversaries can modify or remove without degrading utility, PKF maps numerical attributes to a discrete-time signal, embeds a sinusoidal watermark, and detects its spectral evidence. Its analysis bounds the attack-induced perturbation under which detection succeeds with high probability. Experiments on two datasets show superior robustness over six baselines under six watermark-removal attacks. RaMark is a robust watermarking method for ownership verification of tabular data generated by generative models. It introduces radioactivity, the property that a watermark remains detectable under a retraining attack, in which a generative model is trained on watermarked data and used to generate new tuples. RaMark embeds a sinusoidal dependency into the data distribution and detects it through spectral analysis. The analysis shows that when regenerated and watermarked data distributions remain close in Wasserstein-1 distance, their spectral powers remain close with high probability. Experiments on two datasets show stronger robustness than seven baselines under retraining attacks. LoMark is a fragile watermarking method for integrity verification of relational databases under sparse tampering. It uses primary key set reconciliation to localize inserted and deleted tuples and group testing to localize value-modified tuples. Theoretical guarantees characterize when localization succeeds with high probability and guide parameter selection under a verification metadata budget. Experiments on four datasets against eight baselines show accurate tuple-level localization using verification metadata amounting to 1% of the database size. Overall, this thesis provides watermarking methods for ownership and integrity verification of released tabular data.","abstract_has_math":false,"creators":["Xin Che"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Computing and Software","school":null,"contributors":[],"advisors":["Lingyang, Chu"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T19:38:20Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/25657"],"render_values":[{"text":"https://doi.org/10.71548/25657","href":"https://doi.org/10.71548/25657","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/11375/33888","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/11375/33888","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F33888","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lingyang, Chu"]},{"key":"dc:contributor.department","label":"Department","values":["Computing and Software"]},{"key":"dc:creator","label":"Author","values":["Xin Che"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-10-26T14:20:55Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/11375/33888","https://doi.org/10.71548/25657"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Tabular data are widely shared for machine learning and data analytics. Once released, their owners need to verify ownership of reused data and verify integrity after unauthorized tampering. This thesis develops three watermarking methods for different verification objectives. PKF is a robust watermarking method for ownership verification of tabular data used to train machine learning models. Without relying on primary keys, which adversaries can modify or remove without degrading utility, PKF maps numerical attributes to a discrete-time signal, embeds a sinusoidal watermark, and detects its spectral evidence. Its analysis bounds the attack-induced perturbation under which detection succeeds with high probability. Experiments on two datasets show superior robustness over six baselines under six watermark-removal attacks. RaMark is a robust watermarking method for ownership verification of tabular data generated by generative models. It introduces radioactivity, the property that a watermark remains detectable under a retraining attack, in which a generative model is trained on watermarked data and used to generate new tuples. RaMark embeds a sinusoidal dependency into the data distribution and detects it through spectral analysis. The analysis shows that when regenerated and watermarked data distributions remain close in Wasserstein-1 distance, their spectral powers remain close with high probability. Experiments on two datasets show stronger robustness than seven baselines under retraining attacks. LoMark is a fragile watermarking method for integrity verification of relational databases under sparse tampering. It uses primary key set reconciliation to localize inserted and deleted tuples and group testing to localize value-modified tuples. Theoretical guarantees characterize when localization succeeds with high probability and guide parameter selection under a verification metadata budget. Experiments on four datasets against eight baselines show accurate tuple-level localization using verification metadata amounting to 1% of the database size. Overall, this thesis provides watermarking methods for ownership and integrity verification of released tabular data."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy (PhD)"]},{"key":"dc:title","label":"Title","values":["Robust and Fragile Watermarking for Ownership and Integrity Verification of Tabular Data"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lingyang, Chu"],"dc:contributor.department":["Computing and Software"],"dc:creator":["Xin Che"],"dc:date.accessioned":["2026-10-26T14:20:55Z"],"dc:date.issued":["2026"],"dc:description.abstract":["Tabular data are widely shared for machine learning and data analytics. Once released, their owners need to verify ownership of reused data and verify integrity after unauthorized tampering. This thesis develops three watermarking methods for different verification objectives. PKF is a robust watermarking method for ownership verification of tabular data used to train machine learning models. Without relying on primary keys, which adversaries can modify or remove without degrading utility, PKF maps numerical attributes to a discrete-time signal, embeds a sinusoidal watermark, and detects its spectral evidence. Its analysis bounds the attack-induced perturbation under which detection succeeds with high probability. Experiments on two datasets show superior robustness over six baselines under six watermark-removal attacks. RaMark is a robust watermarking method for ownership verification of tabular data generated by generative models. It introduces radioactivity, the property that a watermark remains detectable under a retraining attack, in which a generative model is trained on watermarked data and used to generate new tuples. RaMark embeds a sinusoidal dependency into the data distribution and detects it through spectral analysis. The analysis shows that when regenerated and watermarked data distributions remain close in Wasserstein-1 distance, their spectral powers remain close with high probability. Experiments on two datasets show stronger robustness than seven baselines under retraining attacks. LoMark is a fragile watermarking method for integrity verification of relational databases under sparse tampering. It uses primary key set reconciliation to localize inserted and deleted tuples and group testing to localize value-modified tuples. Theoretical guarantees characterize when localization succeeds with high probability and guide parameter selection under a verification metadata budget. Experiments on four datasets against eight baselines show accurate tuple-level localization using verification metadata amounting to 1% of the database size. Overall, this thesis provides watermarking methods for ownership and integrity verification of released tabular data."],"dc:description.degree":["Doctor of Philosophy (PhD)"],"dc:identifier.uri":["https://hdl.handle.net/11375/33888","https://doi.org/10.71548/25657"],"dc:language.iso":["en"],"dc:title":["Robust and Fragile Watermarking for Ownership and Integrity Verification of Tabular Data"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:38:20Z"}