Dell Products Inc.

Vinicius Facco Rodrigues

Cristiano André Da Costa

Rodrigo Da Rosa Righi

Tanuj Arcot Omkar

Rodrigo De Souza Scorsatto

Lucas Micol Policarpo

Jorge Luis Victória Barbosa

Rodolfo Stoffel Antunes

Joubert De Castro Lima

Jonathan Leventis

Thaynã Da Silva França

Kasey Mallette

Aravind Reddy Lakkadi

Victor Da Cruz Ferreira

Reducing network communication overhead in computing systems. In a computing system that uses messages to achieve consensus, a communication protocol is adapted to include row-wise and column-wise broadcast phases. This reduces communication complexity significantly compared to all-to-all communication protocols. In the event of faulty nodes, a post phase is introduced that allows additional communications in order to achieve consensus. Even when the post phase is required, the communication complexity is reduced compared to all-to-all based communication protocols.

Network topology oriented Byzantine fault tolerant system

Methods, apparatus, and processor-readable storage media for detection of anomalous behavior on online platforms using machine learning techniques are provided herein. An example method includes obtaining a set of machine learning models configured to detect anomalous behavior associated with users interacting with an online platform and performing an incremental machine learning process on one or more of the machine learning models in the set. The incremental machine learning process may include obtaining data related to interactions of users with the online platform, updating at least one of the machine learning models in the set based on the obtained data, comparing the machine learning models, and selecting one of the machine learning models from the set to be used by the online platform based on the comparison. The method may further include determining, utilizing the selected machine learning model, that a given user is exhibiting anomalous behavior on the online platform.

Detection of anomalous behavior on online platforms using machine learning techniques

An apparatus comprises a processing device configured to monitor for events associated with users interacting with an e-commerce platform, to identify an event type of a given event associated with a given user interacting with the e-commerce platform, and to select, based on the identified event type, at least one of a plurality of machine learning models configured to characterize different types of potentially malicious behavior on the e-commerce platform. The processing device is also configured to determine, utilizing the selected at least one machine learning model, whether the given user is exhibiting at least one of the different types of potentially malicious behavior. The processing device is also configured, responsive to determining that the given user is exhibiting at least one of the different types of potentially malicious behavior, to initiate actions on the e-commerce platform to prevent or mitigate an effect of the potentially malicious behavior.

Machine learning-based detection of potentially malicious behavior on an e-commerce platform

Growing community of inventors

Sao Paulo, Brazil

Vinicius Facco Rodrigues