Isolating data for analysis to avoid malicious attacks

A system comprising:

• a processor;
• and,
• a memory storing machine-readable instructions, which when executed by the processor, cause the processor to perform one or more operations, the operations comprising:
• selecting, based at least on one or more features associated with a file, a first machine learning model and a second machine learning model;
• determining, by the first machine learning model and the second machine learning model, a classification indicative of whether the file is safe for processing by a primary operating environment, the determining of the classification performed in an isolated operating environment, the classification being determined by at least:
• weighting a first output of the first machine learning model, the first output being weighted based on a first error rate of the first machine learning model;
• weighting a second output of the second machine learning model, the second output being weighted based on a second error rate of the second machine learning model;
• and
• generating the classification by at least combining the first output and the second output;
• and
• providing, in response to the classification indicating the file as safe for processing, the file to the primary operating environment for processing by the primary operating environment;
• and
• preventing, in response to the classification indicating the file as unsafe for processing, the file from being processed by the primary operating environment.

A non-transitory computer program product storing instructions which, when executed by at least one hardware data processor forming part of at least one computing system, result in operations comprising:

• selecting, based at least on one or more features associated with a file, a first machine learning model and a second machine learning model;
• determining, by the first machine learning model and the second machine learning model, a classification indicative of whether the file is safe for processing by a primary operating environment, the determining of the classification performed in an isolated operating environment, the classification being determined by at least:
• weighting a first output of the first machine learning model, the first output being weighted based on a first error rate of the first machine learning model;
• weighting a second output of the second machine learning model, the second output being weighted based on a second error rate of the second machine learning model;
• and
• generating the classification by at least combining the first output and the second output;
• and
• providing, in response to the classification indicating the file as safe for processing, the file to the primary operating environment for processing by the primary operating environment;
• and
• preventing, in response to the classification indicating the file as unsafe for processing, the file from being processed by the primary operating environment.