Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Accurately identifying members of training data in variational autoencoders by reconstruction error

Accurately identifying members of training data in variational autoencoders by reconstruction error

US Patent 11501172 · Granted Nov 15, 2022

Estimated economic value: $4,248,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Directed fuzzing for vulnerability detection2025
Measuring confounding effects in machine learning-based vulnerability discovery2025
Performance benchmarking with cascaded decryption2025
Directed fuzzing for vulnerability detection2025
Data obscuring for privacy-enhancement2025
Interpretability framework for differentially private deep learning2024
Interpretability framework for differentially private deep learning2024
Differentially private variational autoencoders for data obfuscation2024
Interpretability framework for differentially private deep learning2024
Interpretability framework for differentially private deep learning2024
Differential privacy to prevent machine learning model membership inference2022
Computer systems for detecting training data usage in generative models2022