Method and system for separating and recalibrating feature for adversarial robustness

A non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to perform a feature separation and recalibration method on a computer device, the feature separation and recalibration method comprising:

• disentangling an input feature map into a first feature defined as a robust feature and a second feature defined as a non-robust feature, based on a robustness score;
• generating a recalibrated feature by recalibrating activation of the second feature;
• and
• generating an output feature map by combining the first feature and the recalibrated feature.

A computer device comprising:

• at least one processor configured to execute a computer-readable instruction,
• wherein the at least one processor is configured to,
• disentangle an input feature map into a first feature defined as a robust feature and a second feature defined as a non-robust feature, based on a robustness score,
• generate a recalibrated feature by recalibrating activation of the second feature, and
• generate an output feature map by combining the first feature and the recalibrated feature.