International Business Machines Corporation

Martin Wistuba

Mathieu Sinn

Ngoc Minh Tran

Ambrish Rawat

Beat Buesser

Maria-Irina Nicolae

Bei Chen

Akihiro Kishimoto

Radu Marinescu

Thanh Lam Hoang

Parikshit Ram

Mansura Habiba

Gokhan Sagirlar

Djallel Bouneffouf

Sharon Qian

Suwen Lin

Ambrish Rwat

Embodiments are disclosed for a method. The method includes validating training data that is provided for training a machine learning model using ordinary differential equations. The method further includes generating pre-processed training data from the validated training data by generating encrypted training data from the validated training data using homomorphic encryption and generating random noise based on the validated training data. The method also includes training the machine learning model adversarially with the pre-processed training data.

Security as a service for machine learning

Embodiments for automatic data preprocessing for a machine learning operation by a processor. For each data instance in a set of data instances, a sequence of actions may be automatically learned in a reinforcement learning environment to be applied for preprocessing each data instance separately. Each of the data instances may be preprocessed for use by one or more machine learning models according to the learned sequence of actions.

Automatic data preprocessing

Various embodiments are provided for securing machine learning models by one or more processors in a computing system. One or more hardened machine learning models that are secured against adversarial attacks are provided by applying one or more of a plurality of combinations of selected preprocessing operations from one or more machine learning models, a data set used for hardening the one or more machine learning models, a list of preprocessors, and a selected number of learners.

Learning input preprocessing to harden machine learning models

Systems, computer-implemented methods, and computer program products to facilitate automated generation of a machine learning pipeline based on a pipeline grammar are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a pipeline structure generator component that generates a machine learning pipeline structure based on a pipeline grammar. The computer executable components can further comprise a pipeline optimizer component that selects one or more machine learning modules that achieve a defined objective to instantiate a machine learning pipeline based on the machine learning pipeline structure.

Automated generation of a machine learning pipeline

Various embodiments are provided for automating decision making for a neural architecture search by one or more processors in a computing system. One or more specifications may be automatically selected for a dataset, tasks, and one or more constraints for a neural architecture search. The neural architecture search may be performed based on the one or more specifications. A deep learning model may be suggested, predicted, and/or configured for the dataset, the tasks, and the one or more constraints based on the neural architecture search.

Automated decision making for neural architecture search

One or more hardened machine learning models are secured against adversarial attacks by adding adversarial protection to one or more previously trained machine learning models. To generate the hardened machine learning models, the previously trained machine learning models are retrained and extended using preprocessing layers or using additional network layers which test model performance on benign or adversarial samples. A rollback strategy is additionally implemented to retain intermediate model states during the retraining to provide recovery if a training collapse is detected.

Adding adversarial robustness to trained machine learning models

Embodiments for providing adversarial protection to computing display devices by a processor. Security defenses may be provided on one or more image display devices against automated media analysis by using adversarial noise, an adversarial patch, or a combination thereof.

Providing adversarial protection for electronic screen displays

A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial example; training a defender to protect the model from the first adversarial example by updating a strategy of the defender based on predictive results from classifying the first adversarial example; updating the attack tactic based on the predictive results from classifying the first adversarial example; generating a second adversarial example by modifying the original input using the updated attack tactic, wherein the trained defender does not protect the model from the second adversarial example; and training the defender to protect the model from the second adversarial example by updating the at least one strategy of the defender based on results obtained from classifying the second adversarial example.

Protecting a machine learning model

Embodiments for providing adversarial protection of speech in audio signals by a processor. Security defenses on one or more audio devices may be provide against automated audio analysis of audio signals by using adversarial noise.

Growing community of inventors

Dublin, Ireland

Martin Wistuba