System and method for detecting malicious attacks targeting artificial intelligence models
US12306935B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 29, 2022 |
| Grant date | May 20, 2025 |
| Priority date | — |
| Expiry date | Aug 19, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F21/57
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and systems for detecting malicious attacks targeting an artificial intelligence (AI) model are disclosed. To detect malicious attacks targeting an AI model, data sets and data sources from which the data sets are obtained may be analyzed. A severity level of risk associated with using the data set to re-train the AI model may be obtained. If the severity level of risk exceeds a re-training risk threshold, the data set may not be used to re-train the AI model. To reduce the likelihood of generating tainted inferences that may significantly impact operation of a downstream consumer, a magnitude of impact of potential inferences derived from the data set may be obtained. If the magnitude of impact of potential inferences derived from the data set exceeds a magnitude threshold, the data set may be discarded without generating any inferences.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.