Harman International Industries, Inc.

George Jose

Shachar Mendelowitz

Rajesh Biswal

Aashish Kumar

Alexander Kreines

Nir Morgulis

Srinivas Kruthiventi Subrahmanyeswara Sai

Sambuddha Saha

Srinivas Kruthiveti Subrahmanyeswara Sai

Jigar Mistry

Techniques are disclosed for detecting adversarial attacks. A machine learning (ML) system processes the input into and output of a ML model using an adversarial detection module that does not include a direct external interface. The adversarial detection module includes a detection model that generates a score indicative of whether the input is adversarial using, e.g., a neural fingerprinting technique or a comparison of features extracted by a surrogate ML model to an expected feature distribution for the output of the ML model. In turn, the adversarial score is compared to a predefined threshold for raising an adversarial flag. Appropriate remedial measures, such as notifying a user, may be taken when the adversarial score satisfies the threshold and raises the adversarial flag.

Defending machine learning systems from adversarial attacks

Growing community of inventors

Bengaluru, India

George Jose