Patents
US 12737495 B2: Machine learning training with enforced differential privacy using secure multi-party computation
- Granted
- 2026-09-15
- Filed
- 2024-07-01 application 18760772
- Type
- Utility · 19 claims
- Elsewhere
- Google Patents ↗ · USPTO patent document ↗ · USPTO Patent Center record ↗
Abstract
Methods and systems for training machine learning models with enforced differential privacy using Secure Multi-Party Computation (SMPC) protocols are disclosed. A method for generating random bits for a Secure Multi-Party Computation (SMPC) protocol in a machine learning model training system includes locally generating, at each participating node, a plurality of random bits using a cryptographically secure pseudorandom number generator (CSPRNG). The locally generated random bits provided as input to the SMPC protocol and combined using an exclusive or (XOR) or addition operation to produce a set of combined random bits. A statistical sampling process for Differential Privacy (DP) is performed using the combined random bits as inputs. The perturbed training data is then utilized in the SMPC protocol to train the machine learning model.
Source: PTBLXML, file of 2026-09-15 (ipgb20260915.xml).
Assignees
| Assignee | Type | Place | Also on furp.org | Source |
|---|---|---|---|---|
| Enveil, Inc. 31 patents | US company or organization | Fulton, MD | ENVEIL, INC. State business registration EXACT high confidence: identical full name and state Enveil, Inc. Form D issuer EXACT high confidence: identical full name and state ENVEIL, INC. Federal lobbying client EXACT high confidence: identical full name and state | PTBLXML, file of 2026-09-15 |
Inventors
| Inventor | Place | Patents | Person page | Source |
|---|---|---|---|---|
| Ryan Carr | Fulton, MD | 34 | PTBLXML, file of 2026-09-15 | |
| Jeffery Hein | Glen Burnie, MD | PTBLXML, file of 2026-09-15 | ||
| Guillermo Gutierrez | McLean, VA | PTBLXML, file of 2026-09-15 | ||
| Lauren Procz | Crofton, MD | PTBLXML, file of 2026-09-15 | ||
| Claire Tomesch | Baltimore, MD | PTBLXML, file of 2026-09-15 | ||
| Yizhou Li | McLean, VA | PTBLXML, file of 2026-09-15 |
CPC categories
| Subclass | Category | First group | Source |
|---|---|---|---|
| G06F | Electric digital data processing | G06F21/6245 | PTBLXML, file of 2026-09-15 |
| H04L | Transmission of digital information, e.g. telegraphic communication | H04L9/0643 | PTBLXML, file of 2026-09-15 |
| G06N | Computing arrangements based on specific computational models | G06N20/00 | PTBLXML, file of 2026-09-15 |
Cooperative Patent Classification, as currently assigned (one row per subclass).
Assignments and security interests
No recorded assignments or security interests on file for this patent.
USPTO bulk data: PatentsView granted patents, disambiguated (PVGPATDIS) for patents, assignees, inventors, places and CPC categories; the USPTO Patent Assignment Dataset (ECORSEXC) for assignments and security interests. Patents filed in the last 20 years. No claims or full text. Links to other records are by name (and state): EXACT means the identical full name and state; FUZZY means a looser name match, with the confidence shown.