Identifying adversarial attacks with advanced subset scanning

An apparatus for detecting whether a given item within input data is anomalous, the apparatus comprising:

• a memory;
• and
• at least one processor coupled to the memory, the processor being operative:
• to extract activations at respective nodes of an autoencoder trained on the data, the activations comprising activations at the respective nodes for the given item within the data and for one or more other items within the data;
• to calculate p-values corresponding to the respective nodes, wherein the p-value for a given node represents a proportion of the activations at the given node for the other items which are greater than the activations at the given node for the given item;
• to determine at least one score at least in part by scanning for a subset of the respective nodes which maximizes a statistical scoring function applied to the corresponding p-values;
• and
• to provide a visualization of at least the given item within the input data to a human user.

A computer program product for solving a dynamical system, the computer program product comprising a non-transitory machine-readable storage medium having machine-readable program code embodied therewith, said machine-readable program code comprising machine-readable program code configured:

• to extract activations at respective nodes of an autoencoder trained on the data, the activations comprising activations at the respective nodes for the given item within the data and for one or more other items within the data;
• to calculate p-values corresponding to the respective nodes, wherein the p-value for a given node represents a proportion of the activations at the given node for the other items which are greater than the activations at the given node for the given item;
• to determine at least one score at least in part by scanning for a subset of the respective nodes which maximizes a statistical scoring function applied to the corresponding p-values;
• and
• to provide a visualization of at least the given item within the input data to a human user.