P

Inventor

MUMMADI CHAITHANYA KUMAR

US13 patents

Patents

13 patents
US10824122B2Nov 3, 2020

Method and device for improving the robustness with respect to “adversarial examples”

BOSCH GMBH ROBERT42 citations92
US11055632B2Jul 6, 2021

Method and device for improving the robustness against “adversarial examples”

BOSCH GMBH ROBERT0 citations61
US12547774B2Feb 10, 2026

System and method with multi-size masking for certified defenses against adversarial patches

BOSCH GMBH ROBERT0 citations58
US11947625B2Apr 2, 2024

Data-based updating of the training of classifier networks

BOSCH GMBH ROBERT1 citations58
US10331091B2Jun 25, 2019

Method and device for improving the robustness with respect to “adversarial examples”

BOSCH GMBH ROBERT0 citations50
US12469271B2Nov 11, 2025

Training neural networks with a lesser requirement for labelled training data

BOSCH GMBH ROBERT0 citations48
US12468937B2Nov 11, 2025

Device and method for training a classifier using an invertible factorization model

BOSCH GMBH ROBERT0 citations48
US12236695B2Feb 25, 2025

System and method with masking for certified defense against adversarial patch attacks

BOSCH GMBH ROBERT0 citations48
US12400006B2Aug 26, 2025

System and method with masking for certified defenses against adversarial patches

BOSCH GMBH ROBERT0 citations47
US12394028B2Aug 19, 2025

System and method with masking and inpainting strategy for generic defense against patch attacks

BOSCH GMBH ROBERT0 citations47
US12243283B2Mar 4, 2025

Device and method for determining a semantic segmentation and/or an instance segmentation of an image

BOSCH GMBH ROBERT0 citations47
US12536339B2Jan 27, 2026

Device and method for determining adversarial patches for a machine learning system

BOSCH GMBH ROBERT0 citations45
US12340572B2Jun 24, 2025

Device and method to adapt a pretrained machine learning system to target data that has different distribution than the training data without the necessity of human annotations on target data

BOSCH GMBH ROBERT0 citations44