Hrl Laboratories, LLC

Pape Sylla

Michael A Warren

Aleksey Nogin

Christopher Serrano

David Naumann

Andrey Chudnov

Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.

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

Described is a system for automatically generating images that satisfy specific image properties. Using a code parser component, a tensor expression intermediate representation (IR) of a deep neural network code is produced. A specification describing a set of image properties is parsed in a fixed formal syntax. The tensor expression IR and the specification is input into a rewriting and analysis engine. The rewriting and analysis engine queries an external solver to obtain pixel values satisfying the specification. When pixel values satisfying the specification can be found in a fixed time period, the rewriting and analysis engine combines the pixel values into an image that satisfies the specification and outputs the image.

Automatic generation of images satisfying specified neural network classifier properties

Described is a system for enforcing software policies. The system transforms an original software by inserting additional instructions into the original software. The additional instructions have the effect of determining, at run-time, whether proceeding with execution of the original software is in accordance with a predefined policy. Transforming the original software relies on software analysis to determine whether any run-time checks normally inserted into the original software can be safely omitted. The transformed software prevents unauthorized information from passing to the network.

Growing community of inventors

Thousand Oaks, CA, United States of America

Pape Sylla