Detection of an adversarial backdoor attack on a trained model at inference time
US11601468B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 25, 2019 |
| Grant date | Mar 7, 2023 |
| Priority date | — |
| Expiry date | Sep 18, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems, computer-implemented methods, and computer program products that can facilitate detection of an adversarial backdoor attack on a trained model at inference time are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a log component that records predictions and corresponding activation values generated by a trained model based on inference requests. The computer executable components can further comprise an analysis component that employs a model at an inference time to detect a backdoor trigger request based on the predictions and the corresponding activation values. In some embodiments, the log component records the predictions and the corresponding activation values from one or more layers of the trained model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.