Pillutla et al., 2024 - Google Patents
Unleashing the power of randomization in auditing differentially private mlPillutla et al., 2024
View PDF- Document ID
- 9321169627406177015
- Author
- Pillutla K
- Andrew G
- Kairouz P
- McMahan H
- Oprea A
- Oh S
- Publication year
- Publication venue
- Advances in Neural Information Processing Systems
External Links
Snippet
We present a rigorous methodology for auditing differentially private machine learning by adding multiple carefully designed examples called canaries. We take a first principles approach based on three key components. First, we introduce Lifted Differential Privacy …
- 241000287231 Serinus 0 abstract description 159
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30386—Retrieval requests
- G06F17/30424—Query processing
- G06F17/30477—Query execution
- G06F17/30507—Applying rules; deductive queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30386—Retrieval requests
- G06F17/30424—Query processing
- G06F17/30533—Other types of queries
- G06F17/30539—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30386—Retrieval requests
- G06F17/30424—Query processing
- G06F17/30477—Query execution
- G06F17/30483—Query execution of query operations
- G06F17/30486—Unary operations; data partitioning operations
- G06F17/30489—Aggregation and duplicate elimination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30386—Retrieval requests
- G06F17/30424—Query processing
- G06F17/30442—Query optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30587—Details of specialised database models
- G06F17/30592—Multi-dimensional databases and data warehouses, e.g. MOLAP, ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30386—Retrieval requests
- G06F17/30389—Query formulation
- G06F17/30398—Query predicate definition using graphical user interfaces, including menus and forms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30557—Details of integrating or interfacing systems involving at least one database management system
- G06F17/3056—Details of integrating or interfacing systems involving at least one database management system between a Database Management System and a front-end application
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30557—Details of integrating or interfacing systems involving at least one database management system
- G06F17/30563—Details for extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30289—Database design, administration or maintenance
- G06F17/30303—Improving data quality; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30587—Details of specialised database models
- G06F17/30595—Relational databases
- G06F17/30604—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06F—ELECTRICAL DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
- G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
- G06F17/30575—Replication, distribution or synchronisation of data between databases or within a distributed database; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computer systems utilising knowledge based models
- G06N5/02—Knowledge representation
- G06N5/022—Knowledge engineering, knowledge acquisition
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pillutla et al. | Unleashing the power of randomization in auditing differentially private ml | |
Nasr et al. | Adversary instantiation: Lower bounds for differentially private machine learning | |
Papernot et al. | Scalable private learning with pate | |
Steinke et al. | Privacy auditing with one (1) training run | |
Kasiviswanathan et al. | What can we learn privately? | |
Guo et al. | Bounding training data reconstruction in private (deep) learning | |
Huang et al. | Cross-validation based K nearest neighbor imputation for software quality datasets: an empirical study | |
Evans et al. | Statistically valid inferences from differentially private data releases, with application to the facebook urls dataset | |
Zhang et al. | Privately learning Markov random fields | |
Sato | Approximate relational Hoare logic for continuous random samplings | |
Nóbrega et al. | Blockchain-based privacy-preserving record linkage: enhancing data privacy in an untrusted environment | |
Tancredi et al. | Regression analysis with linked data: problems and possible solutions | |
Lubars et al. | Correcting the output of approximate graph matching algorithms | |
Xu et al. | Metrics for differential privacy in concurrent systems | |
Gibbons et al. | Quantitative information flow with monads in haskell | |
Leemann et al. | Gaussian membership inference privacy | |
Busa-Fekete et al. | Label differential privacy and private training data release | |
Lu et al. | Eureka: a general framework for black-box differential privacy estimators | |
Lee et al. | Bounds on the power of proofs and advice in general physical theories | |
McVeigh et al. | Practical Bayesian inference for record linkage | |
Alvim et al. | A novel analysis of utility in privacy pipelines, using kronecker products and quantitative information flow | |
Cherubin et al. | Closed-Form Bounds for DP-SGD against Record-level Inference | |
Castellon et al. | DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation | |
Kalemaj et al. | Sublinear-time computation in the presence of online erasures | |
Chen et al. | HOLMES: A Platform for Detecting Malicious Inputs in Secure Collaborative Computation. |