International Business Machines Corporation

Utopus Insights, Inc.

Mathieu Sinn

Bei Chen

Ngoc Minh Tran

Ambrish Rawat

Beat Buesser

Thanh Lam Hoang

Martin Wistuba

Francesco Fusco

Pascal Pompey

Johann-Michael Thiebaut

Maria-Irina Nicolae

Tiep Mai

Vincent Petrus Anthonius Lonij

Jean-Baptiste Remi Fiot

Michael Wurst

Joern Ploennigs

Killian Levacher

Anika Schumann

Carlos A Alzate Perez

Stefano Braghin

Eric P Bouillet

Francesco Calabrese

Fabio Pinelli

Sean A McKenna

Ulrike Fischer

Ji W Yoon

Amith Singhee

Umamaheswari C Devi

Fearghal O'Donncha

Amar Prakash Azad

Vincent Lonij

Fearghal O'donncha

Hessel Tuinhof

Sharon Qian

Suwen Lin

Various embodiments are provided for automated evaluation of machine learning models in a computing environment by one or more processors in a computing system. A level of robustness of a machine learning model against adversarial whitebox operations may be evaluated and determined by applying a data set used for testing the machine learning model, one or more adversarial operation objectives, an adversarial threat model, and a selected number of hyperparameters. Results from the adversarial operation may be analyzed and a modified machine learning model may be generated while performing the evaluating and determining.

Automated evaluation of machine learning models

Adversarial attack detection operations may be applied on one or more deep generative models for defending deep generative models from adversarial attacks. The adversarial attack may be detected on the one or more deep generative models based on the one or more of a plurality of adversarial attack detection operations. The one or more deep generative models may be sanitized based on the adversarial attack.

Defending deep generative models against adversarial attacks

Techniques of facilitating deep learning model rescaling by computing devices. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise: a rescaling component; and a forecasting component. The rescaling component can determine a scaling ratio that maps low mesh resolution predictive data output by a partial differential equation (PDE)-based model for a sub-domain to high-resolution observational or ground-truth data for a domain comprising the sub-domain. The forecasting component can generate high mesh resolution predictive data for the domain with a machine-learning model using input data of the PDE-based model and the scaling ratio.

Superresolution and consistency constraints to scale up deep learning models

Various embodiments manage energy generation in a power generation and distribution system. In one embodiment, a set of residual load data is obtained for a given period of time measured at one or more nodes within a power generation and distribution system. The set of residual load data encodes a set of power flow signals. The set of residual load data is analyzed. An amount of power contributed to the set of residual load data by at least one energy generator class is determined based on the analysis of the set of residual load data.

Real-time estimation of contributions from classes of energy generators in residual load signals

A computing device configured for automatic selection of model parameters includes a processor and a memory coupled to the processor. The memory stores instructions to cause the processor to perform acts including providing an initial set of model parameters and initial condition information to a model based on historical data. A model generates data based on the model parameters and the initial condition information. After determining whether the model-generated data is similar to an observed data, updated model parameters are selected for input to the model based on the determined similarity.

System for continuous update of advection-diffusion models with adversarial networks

One or more computer processors transmit a machine learning model and an associated loss function to a worker, wherein the worker isolates private data. The one or more computer processors receive a plurality of encrypted gradients computed utilizing the transmitted machine learning model, the associated loss function, and the isolated private data. The one or more computer processors generate a plurality of adversarial perturbations, wherein the plurality of adversarial perturbations includes true perturbations and false perturbations. The one or more computer processors obfuscate the generated plurality of adversarial perturbations. The one or more computer processors transmit the obfuscated adversarial perturbations to the worker. The one or more computer processors harden the machine learning model utilizing the transmitted obfuscated adversarial perturbations and the private data.

Federated private adversarial training

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

Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.

Automatic feature extraction from a relational database

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

Disclosed are techniques for determining data relationships between privacy-restricted datapoints, sourced over a computer network, which require data privacy measures concealing at least some datapoints from other clients in the network that the datapoint respectively do not originate from. A first client encrypts a first datapoint with a public key of a public/private encryption scheme and communicates it to the second client along with the public key. The second client encrypts a corresponding second datapoint with the public key, then determines a relationship between the two encrypted datapoints, and communicates the determined relationship to a central client along with the public key. Random noise is encrypted by the central client and added to the determined relationship, then sent together to the first client, followed by decryption by the first client using the private key. The central client extracts the random noise after receiving the decrypted determined relationship.

Preserving inter-party data privacy in global data relationships

A method, computer system, and a computer program product for text data protection is provided. The present invention may include receiving a text data. The present invention may also include identifying a portion of the received text data having a highest impact on a first confidence score associated with a target model prediction. The present invention may further include generating at least one semantically equivalent text relative to the identified portion of the received text data. The present invention may also include determining that the generated at least one semantically equivalent text produces a second confidence score associated with the target model prediction that is less than the first confidence score associated with the target model prediction. The present invention may further include generating a prompt to suggest modifying the identified portion of the received text data using the generated at least one semantically equivalent text.

Text data protection against automated analysis

Embodiments for automatic feature learning for predictive modeling in a computing environment by a processor. A first table and a second table are joined based on an edge between the first table and the second table defined by an entity graph thereby creating a resulting joined table that is connected by a column of data. The resulting joined table is used as an input into one or more neural network operations that transform the resulting joined table to one or more features to predict a target variable.

Automatic feature learning from a relational database for predictive modelling

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.

Growing community of inventors

Dublin, Ireland

Mathieu Sinn