{"paper_id":"2403.14724","title":"Six Levels of Privacy: A Framework for Financial Synthetic Data","authors":["Tucker Balch","Vamsi K. Potluru","Deepak Paramanand","Manuela Veloso"],"paper_date":"2024-03-20","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2403.14724v1","page_url":"https://thequant.space/flowcharts/six-levels-of-privacy-a-framework-for-financial-synthetic-d/","scores":{"empirical_rigor":1.5,"math_complexity":4,"quadrant":"Philosophers"},"proposes":{"status":"available","statement":"The paper introduces a hierarchy of six privacy levels for financial synthetic data, providing progressively stronger privacy protections.","quote":"Accordingly, we introduce a hierarchy of ``levels'' of privacy that are useful for categorizing Synthetic Data generation methods and the progressively improved protections they offer.","summary":"Synthetic Data is increasingly important in financial applications. In addition to the benefits it provides, such as improved financial modeling and better testing procedures, it poses privacy risks as well. Such data may arise from client information, business information, or other proprietary…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"There exists an adversary who aims to extract private information from synthetic data.","type":"other","stated":"explicit","quote":"We assume there exists an adversary who aims to extract private 3 FCRA UDAAP Litigation Risk Competitive Risk Membership Inference Attack Applicable Applicable Applicable N/A Attribute Inference Attack Applicable Applicable Applicable N/A Property Inference Attack N/A N/A Applicable Applicable Model Inference Attack Applicable Applicable Applicable Applicable Table 1: Privacy attacks on synthetic data can lead to","support":"full"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"The six-level hierarchy can guide businesses regarding the security and utility trade‑offs of synthetic data.","kind":"theoretical","quote":"These levels can provide guidance to businesses regarding the security and utility of their Synthetic Data.","support":"full"},{"finding":"Level 3 generative modeling methods offer stronger protection than Levels 1‑2 but remain potentially vulnerable to attacks.","kind":"theoretical","quote":"They offer stronger protection than in Level 1 or Level 2, but are still potentially subject to attack.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":7,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:58:13Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}