ROBUSTNESS AGAINST MANIPULATIONS IN MACHINE LEARNING: abstract simplified (18333487)

• This abstract for appeared for patent application number 18333487 Titled 'ROBUSTNESS AGAINST MANIPULATIONS IN MACHINE LEARNING'

Simplified Explanation

The abstract describes a method that involves receiving data points with different feature values. These data points represent observations of a ground truth, which is represented by the feature vector. The method also involves learning parameters of a machine-learning model based on the observed data points. This model includes statistical models that capture the causal relationship between the feature vector, a latent vector, a classification, and a manipulation vector. The manipulation vector represents the effect of potential manipulations between the ground truth and its observation through the feature vector. The learning process involves mapping between the feature vector, latent vector, classification, and manipulation vector.

Original Abstract Submitted

A method comprising: receiving observed data points each comprising a vector of feature values, wherein for each data point, the respective feature values are values of different features of a feature vector. Each observed data point represents a respective observation of a ground truth as observed in the form of the respective values of the feature vector. The method further comprises learning parameters of a machine-learning model based on the observed data points. The machine-learning model comprises one or more statistical models arranged to model a causal relationship between the feature vector and a latent vector, a classification, and a manipulation vector. The manipulation vector represents an effect of potential manipulations occurring between the ground truth and the observation thereof as observed via the feature vector. The learning comprises learning parameters of the one or more statistical models to map between the feature vector, latent vector, classification and manipulation vector.