Adversarial Input Detection Using Image Processing Techniques (IPT)

Abstract

Modern deep learning models for the computer vision domain are vulnerable against adversarial attacks. Image prepossessing technique based defense against malicious input is currently considered obsolete as this defense is not effective against all types of attacks. The advanced adaptive attack can easily defeat pre-processing based defenses. In this paper, we proposed a framework that will generate a set of image processing sequences (several image processing techniques in a series). We randomly select a set of Image processing technique sequences (IPTS) dynamically to answer the obscurity question in testing time. This paper outlines methodology utilizing varied datasets examined with various adversarial data manipulations. For specific attack types and dataset, it produces unique IPTS. The outcome of our empirical experiments shows that the method can efficiently employ as processing for any machine learning models. The research also showed that our process works against adaptive attacks as we are using a non-deterministic set of IPTS for each adversarial input.