Patent · US Active

Adversarial interpolation backdoor detection

US12019747B2 · kind B2 · utility

0Cited by
3References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 13, 2020
Grant dateJun 25, 2024
Priority date
Expiry dateJun 12, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

One or more computer processors determine a tolerance value, and a norm value associated with an untrusted model and an adversarial training method. The one or more computer processors generate a plurality of interpolated adversarial images ranging between a pair of images utilizing the adversarial training method, wherein each image in the pair of images is from a different class. The one or more computer processors detect a backdoor associated with the untrusted model utilizing the generated plurality of interpolated adversarial images. The one or more computer processors harden the untrusted model by training the untrusted model with the generated plurality of interpolated adversarial images.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.