Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method and system for breaking backdoored classifiers through adversarial examples

Method and system for breaking backdoored classifiers through adversarial examples

US Patent 12210619 · Granted Jan 28, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Methods and systems for training a machine learning model with measurement data 2025
Methods and systems for training a machine learning model with measurement data 2025
System and method for high-resolution blackbox patch attack with Bayesian optimi2025
System and method for utilizing weak learners on large language models2025
System and method for localized text to image generation for free via cross atte2025
System and method for localized text to image generation for free via cross atte2025
Deep equilibrium flow estimation2025
Compound for regulating body weight imbalance, composition thereof and applicati2025
Data augmentation for domain generalization2025
Data augmentation for domain generalization2025
Controller with neural network and improved stability2025
Device and method to improve the robustness against ‘adversarial examples’2025