{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/162918"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/162918","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"When Should Model Updates Propagate?","abstract":"AI supply chains rely increasingly on downstream developers adapting pretrained upstream models. When upstream models are retrained with data deletions (which may be prompted by copyright violations, privacy compliance, or removal of illicit content), it’s unclear if all downstream developers must also undergo costly retraining. In this thesis, we investigate the propagation of data deletions through fine-tuned models within a controlled visual classification setting comprising dog-breed and plane-manufacturer recognition tasks. We show that not all model updates propagate equivalently to downstream tasks, and there is a strong relationship between the deleted data’s relationship to the downstream task and its affect on the downstream model. We demonstrate that neither simple performance metrics (accuracy or F1), nor output-level divergences, nor even embedding-based similarity metrics alone adequately predict when a deletion meaningfully impacts downstream tasks. To overcome these limitations, we introduce an information-theoretic metric grounded in Gaussian mixture modeling (GMM) of embedding distributions, capturing deeper representational shifts. Our proposed approach precisely distinguishes when deletions require downstream retraining, achieving high predictive accuracy and recall without directly accessing retrained downstream models.","abstract_html":"AI supply chains rely increasingly on downstream developers adapting pretrained upstream models. When upstream models are retrained with data deletions (which may be prompted by copyright violations, privacy compliance, or removal of illicit content), it’s unclear if all downstream developers must also undergo costly retraining. In this thesis, we investigate the propagation of data deletions through fine-tuned models within a controlled visual classification setting comprising dog-breed and plane-manufacturer recognition tasks. We show that not all model updates propagate equivalently to downstream tasks, and there is a strong relationship between the deleted data’s relationship to the downstream task and its affect on the downstream model. We demonstrate that neither simple performance metrics (accuracy or F1), nor output-level divergences, nor even embedding-based similarity metrics alone adequately predict when a deletion meaningfully impacts downstream tasks. To overcome these limitations, we introduce an information-theoretic metric grounded in Gaussian mixture modeling (GMM) of embedding distributions, capturing deeper representational shifts. Our proposed approach precisely distinguishes when deletions require downstream retraining, achieving high predictive accuracy and recall without directly accessing retrained downstream models.","abstract_has_math":false,"creators":["Struckman, Isabella Marguerite"],"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":["Mądry, Aleksander"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:21:51Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/162918","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mądry, Aleksander"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Struckman, Isabella Marguerite"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-06T17:34:39Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-10-06T17:34:39Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"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","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/162918"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["AI supply chains rely increasingly on downstream developers adapting pretrained upstream models. When upstream models are retrained with data deletions (which may be prompted by copyright violations, privacy compliance, or removal of illicit content), it’s unclear if all downstream developers must also undergo costly retraining. In this thesis, we investigate the propagation of data deletions through fine-tuned models within a controlled visual classification setting comprising dog-breed and plane-manufacturer recognition tasks. We show that not all model updates propagate equivalently to downstream tasks, and there is a strong relationship between the deleted data’s relationship to the downstream task and its affect on the downstream model. We demonstrate that neither simple performance metrics (accuracy or F1), nor output-level divergences, nor even embedding-based similarity metrics alone adequately predict when a deletion meaningfully impacts downstream tasks. To overcome these limitations, we introduce an information-theoretic metric grounded in Gaussian mixture modeling (GMM) of embedding distributions, capturing deeper representational shifts. Our proposed approach precisely distinguishes when deletions require downstream retraining, achieving high predictive accuracy and recall without directly accessing retrained downstream models."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["When Should Model Updates Propagate?"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mądry, Aleksander"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Struckman, Isabella Marguerite"],"dc:date.accessioned":["2025-10-06T17:34:39Z"],"dc:date.available":["2025-10-06T17:34:39Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["AI supply chains rely increasingly on downstream developers adapting pretrained upstream models. When upstream models are retrained with data deletions (which may be prompted by copyright violations, privacy compliance, or removal of illicit content), it’s unclear if all downstream developers must also undergo costly retraining. In this thesis, we investigate the propagation of data deletions through fine-tuned models within a controlled visual classification setting comprising dog-breed and plane-manufacturer recognition tasks. We show that not all model updates propagate equivalently to downstream tasks, and there is a strong relationship between the deleted data’s relationship to the downstream task and its affect on the downstream model. We demonstrate that neither simple performance metrics (accuracy or F1), nor output-level divergences, nor even embedding-based similarity metrics alone adequately predict when a deletion meaningfully impacts downstream tasks. To overcome these limitations, we introduce an information-theoretic metric grounded in Gaussian mixture modeling (GMM) of embedding distributions, capturing deeper representational shifts. Our proposed approach precisely distinguishes when deletions require downstream retraining, achieving high predictive accuracy and recall without directly accessing retrained downstream models."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/162918"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["When Should Model Updates Propagate?"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:51Z"}