论文标题
FAWA：快速对抗性水印对光学特征识别（OCR）系统的攻击
FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems
论文作者
论文摘要
深神经网络（DNN）显着提高了光学特征识别（OCR）的准确性，并启发了许多重要的应用。不幸的是，OCR还继承了DNN的脆弱性。与五颜六色的香草图像不同，文本图像通常具有清晰的背景。大多数现有的对抗性攻击产生的对抗例子是不自然的，并且严重污染了背景。为了解决这个问题，我们以白盒方式提出了针对基于序列的OCR模型的快速对抗水印攻击（FAWA）。通过将扰动伪装成水印，我们可以使最终的对抗图像对人的眼睛看上去很自然，并获得完美的攻击成功率。 FAWA与基于梯度或基于优化的扰动生成一起工作。在字母级和文字级攻击中，我们的实验表明，除了自然外观外，FAWA还达到了100％的攻击成功率，平均扰动少60％，迭代率平均减少了78％。此外，我们进一步扩展了FAWA，以支持全彩色水印，其他语言，甚至OCR精度增强机制。
Deep neural networks (DNNs) significantly improved the accuracy of optical character recognition (OCR) and inspired many important applications. Unfortunately, OCRs also inherit the vulnerabilities of DNNs under adversarial examples. Different from colorful vanilla images, text images usually have clear backgrounds. Adversarial examples generated by most existing adversarial attacks are unnatural and pollute the background severely. To address this issue, we propose the Fast Adversarial Watermark Attack (FAWA) against sequence-based OCR models in the white-box manner. By disguising the perturbations as watermarks, we can make the resulting adversarial images appear natural to human eyes and achieve a perfect attack success rate. FAWA works with either gradient-based or optimization-based perturbation generation. In both letter-level and word-level attacks, our experiments show that in addition to natural appearance, FAWA achieves a 100% attack success rate with 60% less perturbations and 78% fewer iterations on average. In addition, we further extend FAWA to support full-color watermarks, other languages, and even the OCR accuracy-enhancing mechanism.
