Paper: arXiv 2412.16083
Authors: Timur Sattarov, Marco Schreyer, Damian Borth
Abstract
The increasing demand for privacy-preserving data analytics in various domains necessitates solutions for synthetic data generation that rigorously uphold privacy standards. We introduce the DP-FedTabDiff framework, a novel integration of Differential Privacy, Federated Learning and Denoising Diffusion Probabilistic Models designed to generate high-fidelity synthetic tabular data. This framework ensures compliance with privacy regulations while maintaining data utility. We demonstrate the effectiveness of DP-FedTabDiff on multiple real-world mixed-type tabular datasets, achieving significant improvements in privacy guarantees without compromising data quality. Our empirical evaluations reveal the optimal trade-offs between privacy budgets, client configurations, and federated optimization strategies. The results affirm the potential of DP-FedTabDiff to enable secure data sharing and analytics in highly regulated domains, paving the way for further advances in federated learning and privacy-preserving data synthesis.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced mathematical concepts including differential privacy theory and diffusion model derivations, while also presenting extensive empirical evaluations on real-world tabular datasets to validate the framework’s efficacy and trade-offs.
Research Flowchart
flowchart TD
A["Research Goal: Develop DP-FedTabDiff<br>for privacy-preserving tabular data synthesis"] --> B["Methodology: Federated Diffusion<br>with Differential Privacy"]
B --> C{"Input: Mixed-Type Tabular<br>Datasets from Multiple Clients"}
C --> D["Computations: Federated Training of<br>Denoising Diffusion Probabilistic Models"]
D --> E["Mechanism: Apply Differential Privacy<br>to Gradient Updates"]
E --> F{"Outcomes: Privacy Guarantees<br>vs. Synthetic Data Utility"}
F --> G["Findings: Optimal Trade-offs Achieved<br>Enabling Secure Data Sharing"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes DP-FedTabDiff, a differentially private federated diffusion framework for generating synthetic tabular data.
Source sentence
We introduce the DP-FedTabDiff framework, a novel integration of Differential Privacy, Federated Learning and Denoising Diffusion Probabilistic Models designed to generate high-fidelity synthetic tabular data.
Assumes 6
- The algorithm provides (ε,δ)-differential privacy guarantees. statistical
Source sentence
Formally, a randomized algorithm A provides (ε, δ)-DP if for any two datasets D and D′ differing by one element, and for any subset of outputs S ⊆Range(A): P[A(D) ∈S] ≤eεP[A(D′) ∈S] + δ,
- Federated learning updates use the Gaussian Mechanism with clipped gradients and added Gaussian noise. model
Source sentence
In the proposed DP-FedTabDiff model, the parameter update process is modified to incorporate the Gaussian Mechanism.
- Data are partitioned in a realistic non‑IID and unbalanced way based on a categorical feature. data
Source sentence
To simulate a realistic non-IID and unbalanced data environment for federated training, each dataset is partitioned based on a categorical feature.
- Local client optimization is performed for a fixed number of updates Γ selected from [10, 50, 100, 500, 1000]. execution
Source sentence
We selected Γ values from [10, 50, 100, 500, 1000] and conducted experiments in both IID and non-IID settings, fixing the privacy budget at ε = 1 with five federated clients (λ = 5).
Show 2 more
- The privacy budget is fixed at ε = 1 for certain experiments. statistical
Source sentence
fixing the privacy budget at ε = 1 with five federated clients (λ = 5).
- Numeric attributes are standardized using quantile transformations. data
Source sentence
we employed quantile transformations
Data
- Credit Default (DA) other public
Source sentence
Credit Default3 (DA): This dataset includes 30,000 customers default payments records
- Census Income (DB) other public
Source sentence
Census Income4 (DB): This dataset contains demographic information from the 1994 U.S. Census to predict whether a person earns more than $50,000 per year. In total, there are 32,561 records each encompassing 10 categorical and 3 numerical attributes.
- Philadelphia City Payments (DC) other public
Source sentence
Philadelphia City Payments5 (DC): This dataset consists of 238,894 records. The payments were generated by 58 distinct city departments in 2017. Each payment includes 10 categorical and 1 numerical attribute(s).
- Marketing (DD) other public
Source sentence
Marketing6 (DD) This dataset contains 45,211 customer records of a bank from 2008 to 2010, used to predict whether a client will subscribe to a term deposit. Each record includes 10 categorical and 6 numerical attributes.
Costs
Not applicable
Finds 5
- 100 local updates provide an optimal trade‑off between privacy, utility, and fidelity in both IID and non‑IID settings, reducing training time from 28 h to 3.5 h. performance
Source sentence
Our findings indicate that 100 local updates provide an optimal trade-off between privacy, utility, and fidelity in both IID and non-IID settings. Additionally, this choice significantly reduced the overall training time from 28 hours (Γ = 1000) to 3.5 hours (Γ = 100).
- Increasing the number of local optimization updates raises average privacy risk across all datasets, peaking at 500 updates. other
Source sentence
We observed an increase in the average privacy risk across all datasets with more local optimization updates in both IID and non-IID settings, peaking at 500 updates (see Figure 4).
- In the IID setting, more client updates consistently improve utility and fidelity performance. performance
Source sentence
For utility and fidelity, increasing the number of client updates in the IID setting (see Figure 4b) consistently improved performance.
- In the non‑IID setting, performance declines after a threshold of Γ = 100 due to heterogeneous data distributions. performance
Source sentence
performance declined after a threshold of Γ = 100. The decline is caused by heterogeneous data distributions among clients.
- More local updates reduce privacy protection, indicating a trade‑off between local computation and privacy. other
Source sentence
The results suggest that more local updates reduce privacy protection.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 25 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (314)
- Diffusion Models in Vision: A Survey (2023)
- Findiff: Diffusion models for financial tabular data generation — → 2309.01472
- Phoenix: A Federated Generative Diffusion Model (2023) — link
- Training Diffusion Models with Federated Learning: A Communication-Efficient Model for Cross-Silo Federated Image Generation (2023)
- LLM-Grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (2023) — link
- Training Diffusion Models with Reinforcement Learning (2023) — link
- Masked Diffusion Transformer is a Strong Image Synthesizer (2023) — link
- Magvit: Masked Generative Video Transformer (2023)
and 306 more
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale (2023) — link
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (2023) — link
- A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (2022)
- Sparks of Artificial General Intelligence: Early Experiments with GPT-4 (2023) — link
- GPT-4 Technical Report (2023) — link
- Llama 2: Open Foundation and Fine-Tuned Chat Models (2023) — link
- TabDDPM: Modelling Tabular Data with Diffusion Models (2023)
- High-Resolution Image Synthesis with Latent Diffusion Models (2022)
- A Survey on Generative Diffusion Model (2022) — link
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (2022)
- Diffusion Models: A Comprehensive Survey of Methods and Applications (2022) — link
- Enhancing IoT Anomaly Detection Performance for Federated Learning (2022)
- Generative Trees: Adversarial and Copycat (2022) — link
- Causal-TGAN: Modeling Tabular Data Using Causally-Aware GAN (2022)
- Diffusion-LM Improves Controllable Text Generation (2022)
- Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing (2022)
- Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits (2022)
- CoderL: Mastering Code Generation Through Pretrained Models and Deep Reinforcement Learning (2022)
- Make-a-Video: Text-to-Video Generation Without Text-Video Data (2022) — link
- CodeT: Code Generation with Generated Tests (2022) — link
- Competition-Level Code Generation with AlphaCode (2022)
- Differentially Private Synthetic Medical Data Generation Using Convolutional GANs (2022)
- Equivariant Diffusion for Molecule Generation in 3D (2022)
- Torsional Diffusion for Molecular Conformer Generation (2022)
- Image Super-Resolution via Iterative Refinement (2022)
- Label-Efficient Semantic Segmentation with Diffusion Models (2021)
- Variational Diffusion Models (2021)
- SdEdit: Image Synthesis and Editing with Stochastic Differential Equations (2021) — link
- Structured Denoising Diffusion Models in Discrete State-Spaces (2021)
- CSDI: Conditional Score-Based Diffusion Models for Probabilistic Time Series Imputation (2021)
- Multidimensional Audit Data Selection (MADS) Research Project
- On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? (2021)
- A Survey on Federated Learning (2021)
- OCT-GAN: Neural ODE-Based Conditional Tabular GANs (2021)
- GANBLR: A Tabular Data Generation Model (2021)
- Zero-Shot Text-to-Image Generation (2021)
- CTAB-GAN: Effective Table Data Synthesizing (2021)
- Liability for AI: Public Policy Considerations (2021)
- CRYPTGPU: Fast Privacy-Preserving Machine Learning on the GPU (2021) — link
- Managing Bias in Machine Learning Projects (2021)
- Improved Denoising Diffusion Probabilistic Models (2021)
- Diffusion Models Beat GANs on Image Synthesis (2021)
- Management of Artificial Intelligence: Feasibility, Desirability and Viability (2021)
- Towards a Conceptual Framework on the Importance of Privacy and Security Concerns in Audit Data Analytics (2021)
- A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things (2021) — link
- Deep Learning f "u r die Wirtschaftspr "u fung-Eine Darstellung von Theorie, Funktionsweise und Anwendungsm "o glichkeiten (2021)
- An Incentive Mechanism for Cross-Silo Federated Learning: A Public Goods Perspective (2021)
- PySyft: A Library for Easy Federated Learning (2021)
- Conditional Wasserstein GAN-based oversampling of tabular data for imbalanced learning (2021)
- A survey on federated learning systems: Vision, hype and reality for data privacy and protection (2021)
- Embedding Process Mining into Financial Statement Audits (2021)
- Unsupervised anomaly detection for internal auditing: Literature review and research agenda (2021)
- Using Autoencoders for Data-Driven Analysis in Internal Auditing (2021)
- Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks (2021)
- Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks (2021)
- Federated learning: A survey on enabling technologies, protocols, and applications (2020)
- Top cyberthreats targeting accounting firms (2020)
- DiffWave: A Versatile Diffusion Model for Audio Synthesis (2020)
- WaveGrad: Estimating Gradients for Waveform Generation (2020)
- A Systematic Literature Review on Federated Learning: From A Model Quality Perspective (2020) — link
- Score-Based Generative Modeling through Stochastic Differential Equations (2020)
- Generating Synthetic Data in Finance: Opportunities, Challenges and Pitfalls (2020)
- Cryptflow: Secure TensorFlow Inference (2020)
- A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (2020)
- The Artificial Intelligence for Your Financial Management - Digital Posting Assistant for SAP S/4 Hana and SAP ECC (2020)
- Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications (2020)
- Practitioner’s Guide to GAAS 2000 (2000)
- CrypTen: Secure Multi-Party Computation Meets Machine Learning (2020)
- Extracting Training Data from Large Language Models (2020) — link
- The Ethical Implications of Using Artificial Intelligence in Auditing (2020)
- Federated Learning for Medical Imaging (2019) — link
- Language Models are Few-Shot Learners (2020) — link
- Künstliche Intelligenz in der Prüfungspraxis-Eine Bestandsaufnahme aktueller Einsatzmöglichkeiten und Herausforderungen (2020)
- WeBank and Swiss Re Signed Cooperation MoU (2019) — link
- Towards a Human-Like Open-Domain Chatbot (2020) — link
- Throughput-Optimal Topology Design for Cross-Silo Federated Learning (2020)
- Management von K "u nstlicher Intelligenz in Unternehmen (2020)
- Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Neural Networks (2020)
- Classifying Process Deviations with Weak Supervision (2020)
- Autoencoder Neural Networks versus External Auditors: Detecting Unusual Journal Entries in Financial Statement Audits (2020)
- Accounting Journal Reconstruction with Variational Autoencoders and Long Short-term Memory Architecture (2020)
- Wirtschaftspr "u fung: Grundlagen des Betriebswirtschaftlichen Pr "u fungswesens nach Nationalen und Internationalen Normen (2020)
- Denoising Diffusion Probabilistic Models (2020)
- Improved Techniques for Training Score-Based Generative Models (2020)
- How Does Artificial Intelligence Shape the Audit Industry? (2020)
- Privacy in Deep Learning: A Survey (2020) — link
- PyTorch: An Imperative Style, High-Performance Deep Learning Library (2019)
- Examining Automation in Audit (2019)
- A Survey on Deep Learning Techniques for Privacy-Preserving (2019)
- Modeling Tabular Data Using Conditional GAN (2019)
- How to Play Any Mental Game, or a Completeness Theorem for Protocols with Honest Majority (2019)
- Generative Modeling by Estimating Gradients of the Data Distribution (2019)
- Automatic Differentiation in PyTorch (2017)
- Applying Deep Learning to Audit Procedures: An Illustrative Framework (2019)
- Everybody Dance Now (2019)
- Detection of Accounting Anomalies in the Latent Space Using Adversarial Autoencoder Neural Networks (2019)
- Adversarial Learning of Deepfakes in Accounting (2019)
- Ffd: A federated Learning Based Method for Credit Card Fraud Detection (2019)
- Predicting Adverse Drug reactions on Distributed Health Data using Federated Learning (2019)
- Differential privacy-enabled federated learning for sensitive health data (2019) — link
- Federated Wireless Network Intrusion Detection (2019)
- Benchmarking TPU, GPU, and CPU Platforms for Deep Learning (2019) — link
- Diffusion Models Beat GANs on Image Synthesis (2021) — link
- Privacy-Preserving Machine Learning: Threats and Solutions (2019)
- Accounting Firm Data Breaches: One State’s Records (2019)
- California Consumer Privacy Act: What Companies Need to Know (2019)
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019) — link
- Protecting World Leaders Against Deep Fakes (2019)
- Deep Learning-Based Classification of Mesothelioma Improves Prediction of Patient Outcome (2019)
- When Seeing is No Longer Believing (2019) — link
- Advances and Open Problems in Federated Learning (2019) — link
- Explaining Anomalies Detected by Autoencoders Using SHAP (2019) — link
- PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees (2018)
- Practice Aid for Testing Journal Entries and Other Adjustments Pursuant to AU Section 316 (2008) — link
- Innovation and Practice of Continuous Auditing (2018)
- Deepfake Video Detection Using Recurrent Neural Networks (2018)
- The Risk of Machine-Learning Bias (and How to Prevent It) (2018)
- Reducing False Positives in Fraud Detection: Combining the Red Flag Approach with Process Mining (2018)
- Adversarial Text Generation via Feature-Mover’s Distance (2018)
- ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018) — link
- GDPR: The End of Google and Facebook or a New Paradigm in Data Privacy (2018)
- Disentangling by Factorising (2018) — link
- Deep Learning: A Critical Appraisal (2018) — link
- Large Scale GAN Training for High Fidelity Natural Image Synthesis (2018)
- A General Reinforcement Learning Algorithm that Masters Chess, Shogi, and Go through Self-Play (2018)
- Did You Hear That? Adversarial Examples Against Automatic Speech Recognition (2018) — link
- GDPR: Implications for Auditors - A Position Paper (2018)
- Privacy, Algorithms, and Artificial Intelligence (2019)
- Robust Physical-World Attacks on Deep Learning Models (2017) — link
- This PSA About Fake News From Barack Obama Is Not What It Appears (2016) — link
- Deep Learning and the Future of Auditing: How an Evolving Technology Could Transform Analysis and Improve Judgment (2017)
- A Deeper Look at Dataset Bias (2017)
- Data Mining Applications in Accounting: A Review of the Literature and Organizing Framework (2017)
- Detection of Anomalies in Large Scale Accounting Data Using Deep Autoencoder Networks (2018)
- Neural Discrete Representation Learning (2017)
- Adversarial Attacks on Neural Network Policies (2017) — link
- Datenschutz in der Schweiz, Eine Darstellung Aktueller Entwicklungen (2017)
- Membership Inference Attacks Against Machine Learning Models (2017)
- Communication-Efficient Learning of Deep Networks from Decentralized Data (2017)
- Federated Learning: Collaborative Machine Learning Without Centralized Training Data (2017)
- Securing Big Data Provenance for Auditors: The Big Data Provenance Black Box as Reliable Evidence (2016)
- Big Data and Analytics in the Modern Audit Engagement: Research Needs (2017)
- Research Ideas for Artificial Intelligence in Auditing: The Formalization of Audit and Workforce Supplementation (2016)
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence (2016) — link
- Data Mining Journal Entries for Fraud Detection: A Replication of Debreceny and Gray ‘S (2010) (2016)
- New Horizons for a Data-Driven Economy: A Roadmap for Usage and Exploitation of Big Data in Europe (2016)
- Infogan: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016)
- Responsibility, Autonomy and Accountability: Legal Liability for Machine Learning (2016)
- A Survey of Inductive Biases for Factorial Representation-Learning (2016) — link
- Density Estimation Using Real NVP (2016) — link
- Deep Learning (2016)
- Imagineering Audit 4.0 (2016)
- AUDIT 4.0–Digitale Wirtschaftspr "u fung - Der Einsatz von Innovativen Technologien Ver "a ndert Abschlusspr "u fung und-Pr "u fer (2017)
- Attention is All You Need (2017)
- Mastering the Game of Go Without Human Knowledge (2017)
- Privacy-Preserving Information Sharing Within an Audit Firm (2017)
- Ethics of Emerging Information and Communication Technologies - On the Implementation of Responsible Research and Innovation (2017)
- What Do the New EU Data Protection Regulation Mean for You? - The General Data Protection Regulation (2017)
- Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (2016)
- Detecting Fraudulent Financial Reporting Using Financial Ratio (2016)
- YFCC100M: The New Data in Multimedia Research (2016)
- Exploring the Growing Use of Technology in the Audit, with a Focus on Data Analytics (2016)
- Privacy and Data Protection by Design-From Policy to Engineering (2015) — link
- U-Net: Convolutional Networks for Biomedical Image Segmentation (2015)
- Deep Learning (2015)
- Survey Report: “Deep Shift: Technology Tipping Points and Societal Impact” (2015)
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (2015)
- Deep Unsupervised Learning Using Nonequilibrium Thermodynamics (2015)
- Big Data in Accounting: An Overview (2015)
- How Big Data Will Change Accounting (2015)
- Variational Inference with Normalizing Flows (2015) — link
- Multilevel Process Mining for Financial Audits (2015)
- Big Data and Audit Evidence (2015)
- Big Data as Complementary Audit Evidence (2015)
- Big Data Analytics in Financial Statement Audits (2015)
- Differential Privacy and Machine Learning: A Survey and Review (2014) — link
- What Factors Influence Auditors’ Use of Computer-Assisted Audit Techniques? (2014)
- Black’s Law Dictionary (2014)
- Sequence to Sequence Learning with Neural Networks (2014)
- A Field Study on the Use of Process Mining of Event Logs as an Analytical Procedure in Auditing (2014)
- The Algorithmic Foundations of Differential Privacy (2014)
- Auto-Encoding Variational Bayes (2013) — link
- Big Data: A Revolution That Will Transform How We Live, Work, and Think (2013)
- Handbuch für die Kriminalistik (2013)
- A Breach of Client Data: Risks to CPA Firms (2013)
- Intriguing Properties of Neural Networks (2013) — link
- Auditing Journal Entries Using Extreme Value Theory (2013)
- A Review of Financial Accounting Fraud Detection Based on Data Mining Techniques (2013) — link
- Representation Learning: A Review and New Perspectives (2013)
- The Current State of Continuous Auditing and Continuous Monitoring (2012)
- ImageNet: A Large-Scale Hierarchical Image Database (2009)
- Data Mining Techniques for the Detection of Fraudulent Financial Statements (2007)
- Detecting False Financial Statements Using Published Data: Some Evidence from Greece (2002)
- Auditing Journal Entries Using Self-Organizing Map (2012)
- ImageNet Classification with Deep Convolutional Neural Networks (2012)
- The Application of Differential Privacy to Health Data (2012)
- PCAL: A Privacy-Preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning (2020) — link
- Pattern Classification (2012)
- Digitale SAP®-Massendatenanalyse: Risiken Erkennen - Prozesse Optimieren (2011)
- Cluster Analysis for Anomaly Detection in Accounting Data: An Audit Approach (2011)
- A Business Process Mining Application for Internal Transaction Fraud Mitigation (2011)
- Internal Fraud Risk Reduction: Results of a Data Mining Case Study (2010)
- A State of the Art Survey of Fraud Detection Technology (2010)
- Data Mining Journal Entries for Fraud Detection: An Exploratory Study (2010)
- Fraud Detection in ERP Systems Using Scenario Matching (2010)
- Transaction Mining for Fraud Detection in ERP Systems (2010)
- A Comprehensive Survey of Data Mining-Based Fraud Detection Research (2010) — link
- Korruption und Mitarbeiterkriminalität (2009)
- Fraud Analysis Techniques Using ACL (2009)
- Computer-Aided Fraud Prevention and Detection: A Step-by-step Guide (2009)
- A Role Mining Inspired Approach to Representing User Behaviour in ERP Systems (2009)
- SNARE: A Link Analytic System for Graph Labeling and Risk Detection (2009)
- Accountant Confidentiality (2009)
- International Accounting Standard (ISA) 1: Presentation of Financial Statements (2007)
- International Standard on Auditing (ISA) 200: Overall Objectives of the Independent Auditor and the Conduct of an Audit in Accordance with International Standards on Auditing (2009)
- International Standards on Auditing (ISA) 240: The Auditor’s Responsibilities Relating to Fraud in an Audit of Financial Statements (2009)
- International Standard on Auditing (ISA) 530: Audit Sampling and Other Means of Testing (2009)
- Statement on Auditing Standards (SAS) 1: Codification of Auditing Standards and Procedures (1973)
- Auditing Standard (AS) No. 2305: Substantive Analytical Procedures (2010)
- Auditing Standard (AU) Section 329: Substantive Analytical Procedures (2010)
- Handbook of the International Code of Ethics for Professional Accountants (2018)
- Deep Residual Learning for Image Recognition (2016)
- ImageNet Classification with Deep Convolutional Neural Networks (2017)
- Generative Adversarial Nets (2014)
- Evolution of Auditing: From the Traditional Approach to the Future Audit1 (2018)
- A Fully Homomorphic Encryption Scheme (2009)
- Differential Privacy: A Survey of Results (2008)
- Large Scale Detection of Irregularities in Accounting Data (2006)
- Reducing the Dimensionality of Data with Neural Networks (2006)
- Pattern Recognition and Machine Learning (2006)
- Efficient Sampling Design in Audit Data (2005)
- Peer-Based Approach for Analytical Procedures (2006)
- Computer-Assisted Audit Tools and Techniques: Analysis and Perspectives (2003)
- SMOTE: Synthetic Minority Over-Sampling Technique (2002)
- AU Section 316 - Consideration of Fraud in a Financial Statement Audit (2002) — link
- Outlier Detection using Replicator Neural Networks (2002)
- Statistical Fraud Detection: A Review (2002)
- The Essential Turing (2004)
- Gradient-Based Learning Applied to Document Recognition (1998)
- Putting the Enterprise into the Enterprise System (1998)
- Big Data… and the Next Wave of IntraStress (1998)
- Long Short-Term Memory (1997)
- The Five Assertions - A Revisit (1993)
- The Public Accounting Litigation Wars: Will Expert Systems Lead the Next Assault? (1991)
- Audit Technology and the Use of Computer Assisted Audit Techniques (1990)
- How to Play Any Mental Game (1987)
- Protocols for Secure Computations (1982)
- On the Use of Index Models in Analytical Reviews by Auditors (1980)
- Dollar-Unit Sampling: A Practical Guide for Auditors (1979)
- On Data Banks and Privacy Homomorphisms (1978)
- Behavior of Major Statistical Estimators in Sampling Accounting Populations: An Empirical Study (1975)
- The Representation of the Cumulative Rounding Error of an Algorithm as a Taylor Expansion of the Local Rounding Errors (1970)
- Practical Aspects of Statistical Sampling in Auditing (1963)
- Some Studies in Machine Learning Using the Game of Checkers (1959)
- The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain (1958)
- The Law of Anomalous Numbers (1938)
- OED Online (2021)
- Graphics Processing Unit (GPU) - Wikipedia, The Free Encyclopedia (2021) — link
- Tensor Processing Unit (TPU) - Wikipedia, The Free Encyclopedia (2021) — link
- Adam: A method for stochastic optimization (2014) — link
- TabDDPM: Modelling Tabular Data with Diffusion Models (2022) — link
- Flower: A Friendly Federated Learning Research Framework (2022) — link
- Pytorch: An imperative style, high-performance deep learning library (2019)
- The Synthetic data vault (2016) — link
- The K olmogorov- S mirnov test for goodness of fit (1951)
- Pearson correlation coefficient (2009)
- Pros and Cons of GAN Evaluation Measures (2018) — link
- Synthetic Data Generation for Fraud Detection using GANs (2021) — link
- Synthesizing test data for fraud detection systems (2003) — link
- Augmenting medical image classifiers with synthetic data from latent diffusion models (2023) — link
- Synthetic data in machine learning for medicine and healthcare (2021)
- Argmax flows and multinomial diffusion: Learning categorical distributions (2021)
- Modeling tabular data using conditional gan (2019)
- Differentially private diffusion models (2022) — link
- The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. (2009)
- Opacus: U ser-Friendly Differential Privacy Library in PyTorch (2021) — link
- Federated optimization in heterogeneous networks (2020)
- Adaptive federated optimization (2020) — link
- Statistical Decomposition Analysis: With Applications in the Social and Administrative Sciences (1972) — link
- On the translocation of masses (1958) — link
- Jensen‐Shannon Divergence: A Multipurpose Distance for Statistical and Quantum Mechanics (2007) — link
- A unified framework for quantifying privacy risk in synthetic data (2022) — link
- A survey of differentially private generative adversarial networks (2020)
- A Systematic Review of Federated Generative Models (2024) — link
- Gs-wgan: A gradient-sanitized approach for learning differentially private generators (2020)
- SGDE: Secure generative data exchange for cross-silo federated learning (2022)
- Generative models for effective ML on private, decentralized datasets (2019) — link
- FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia
- Federated Synthetic Data Generation with Differential Privacy — link
- DP-CTGAN: Differentially Private Medical Data Generation Using CTGANs — link
- Privacy-Preserving High-Dimensional Data Collection with Federated Generative Autoencoder — link
- Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning (2020) — link
- Our data, ourselves: Privacy via distributed noise generation (2006)
- Deep learning with differential privacy (2016)
- Differentially private secure multi-party computation for federated learning in financial applications (2020)
- FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation (2024) — link
- The algorithmic foundations of differential privacy (2014)
- Six Levels of Privacy: A Framework for Financial Synthetic Data — → 2403.14724
- Scaffold: Stochastic controlled averaging for on-device federated learning (2019) — link
- Opinion 05/2014 on Anonymisation Techniques (2014) — link
- dython (2018) — link
- On the privacy properties of gan-generated samples (2021)
- Generating high-fidelity, synthetic time series datasets with doppelganger (2019) — link
- Imb-FinDiff: Conditional Diffusion Models for Class Imbalance Synthesis of Financial Tabular Data (2024)
- FraudDiffuse: Diffusion-aided Synthetic Fraud Augmentation for Improved Fraud Detection (2024)
- Entity-based Financial Tabular Data Synthesis with Diffusion Models (2024)
2 of 314 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.