Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Deep reinforcement learning based method for surreptitiously generating signals to fool a recurrent neural network

Deep reinforcement learning based method for surreptitiously generating signals to fool a recurrent neural network

US Patent 12073318 · Granted Aug 27, 2024

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Evaluation of air vehicle flight controls2024
Evaluation of air vehicle flight controls2024
Neural network architecture for small LIDAR processing networks for slope estima2024
Neural network architecture for small LIDAR processing networks for slope estima2024
Solving based introspection to augment the training of reinforcement learning ag2023
Solving based introspection to augment the training of reinforcement learning ag2023
Automated system for generating approximate safety conditions for monitoring and2023
Automated system for generating approximate safety conditions for monitoring and2023
Autonomous behavior generation for aircraft2021
Systems and methods for context-aware network message filtering2021
Automatic generation of images satisfying specified neural network classifier pr2021
Automatic generation of images satisfying specified neural network classifier pr2021