Adaptive Adversarial Attack on Scene Text Recognition

Abstract

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks (e.g., C&W attack) require manually tuning hyper-parameters and take a long time to construct an adversarial example, making it impractical to attack real-time systems; (ii) Most of the studies focus on non-sequential tasks, such as image classification, yet only a few consider sequential tasks. In this work, we speed up adversarial attacks, especially on sequential learning tasks. By leveraging the uncertainty of each task, we directly learn the adaptive multi-task weightings, without manually searching hyper-parameters. A unified architecture is developed and evaluated for both non-sequential tasks and sequential ones. To validate the effectiveness, we take the scene text recognition task as a case study. To our best knowledge, our proposed method is the first attempt to adversarial attack for scene text recognition. Adaptive Attack achieves over 99.9\% success rate with 3-6X speedup compared to state-of-the-art adversarial attacks.

arXiv commentTo be appear in INFOCOM 2020, The Eighth International Workshop on Security and Privacy in Big Data

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• Adversarial vulnerability for any classifier
• Delving into adversarial attacks on deep policies
• Deep Structured Output Learning for Unconstrained Text Recognition

Cited by in corpus (3)

• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Scene Text Detection and Recognition: The Deep Learning Era
• AdvGAN++ : Harnessing latent layers for adversary generation