Vorhersage Trainierter Modellschwachstellen unter Verwendung Generativer Bildbearbeitung und Anomaliedetektion

Details

Veröffentlichungs-Nr.

EP4783126

Anmeldetag

9. Januar 2026

Veröffentlichung

29. Juli 2026

Rechtsraum

EP

Abstract

Implementations enable efficient identification of model vulnerabilities and subsequent model improvement without extensive real-world testing, leading to more robust and reliable models. Some implementations are directed to causing a training image to be processed to generate a synthetic image that includes one or more variations to the training image. The training image is one based on which a model has been trained. The variations in the synthetic image can include various changes, such as adding a new object, changing lighting, modifying the background, or altering the position of an object. The synthetic image is processed, using the model, to generate output. This output is then processed to determine whether the synthetic image is an outlier for the model. In response to determining that the synthetic image is an outlier for the model, remediating action(s) are performed, such as causing the model to be further trained based on the synthetic image.

Anmelder

Firma

GDM Holding LLC

Land

🇺🇸 USA