Adversarial Attacks on Binary Image Recognition Systems

Abstract

We initiate the study of adversarial attacks on models for binary (i.e. black and white) image classification. Although there has been a great deal of work on attacking models for colored and grayscale images, little is known about attacks on models for binary images. Models trained to classify binary images are used in text recognition applications such as check processing, license plate recognition, invoice processing, and many others. In contrast to colored and grayscale images, the search space of attacks on binary images is extremely restricted and noise cannot be hidden with minor perturbations in each pixel. Thus, the optimization landscape of attacks on binary images introduces new fundamental challenges.In this paper we introduce a new attack algorithm called Scar, designed to fool classifiers of binary images. We show that Scar significantly outperforms existing L 0 attacks applied to the binary setting and use it to demonstrate the vulnerability of real-world text recognition systems. Scar's strong performance in practice contrasts with hardness results that show the existence of classifiers that are provably robust to large perturbations. In many cases, altering a single pixel is sufficient to trick Tesseract, a popular open-source text recognition system, to misclassify a word as a different word in the English dictionary. We also license software from providers of check processing systems to most of the major US banks and demonstrate the vulnerability of check recognitions for mobile deposits. These systems are substantially harder to fool since they classify both the handwritten amounts in digits and letters, independently. Nevertheless, we generalize Scar to design attacks that fool state-of-the-art check processing systems using unnoticeable perturbations that lead to misclassification of deposit amounts. Consequently, this is a powerful method to perform financial fraud.

Adversarial attacks on spiking convolutional neural networks for event-based vision

“…Despite the growing number of Spiking Neural Network deployed on digital (Davies et al, 2018 ) and analog (Moradi et al, 2018 ) neuromorphic hardware, robustness to adversarial perturbations has received comparatively little attention by the research community. Some methods proposed for attacking binary inputs have focused on brute-force searches with heuristics to reduce the search space (Bagheri et al, 2018 ; Balkanski et al, 2020 ). Algorithms of this family do not scale well to large input sizes, as the number of queries made to the network grows exponentially.…”