Method and system for breaking backdoored classifiers through adversarial examples
US12210619B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 28, 2020 |
| Grant date | Jan 28, 2025 |
| Priority date | — |
| Expiry date | Oct 6, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented method for training a machine learning network includes receiving an input data from one or more sensors, selecting one or more batch samples from the input data, wherein the batch samples include one or more perturbed samples from a source class configured to be misclassified into a target class, identifying the one or more perturbed samples from the one or more batch samples, determining a trigger event in response to identification of a trigger pattern of the one or more batch samples, wherein the trigger pattern induces a pre-determined response on a classifier, outputting a classification in response to identification of the trigger pattern via the classifier, and outputting a set of trigger patterns extracted from the machine-learning network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.