Search Results for author:
Found 4 papers, 2 papers with code
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
In this work, we propose a novel and effective defense mechanism termed the Universal Defensive Underpainting Patch (UDUP) that modifies the underpainting of text images instead of the characters.
Optical Character Recognition
Optical Character Recognition (OCR)
Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Experimental results show that the proposed method can not only detect the adversarial examples with high accuracy, but also detect the specific category of the AEs.
Adversarial Privacy Protection on Speech Enhancement
Experimental results show that generated adversarial examples can erase most content information in original examples or replace it with target speech content through speech enhancement.
An Automated Estimator of Image Visual Realism Based on Human Cognition
In this paper we systematically evaluate factors underlying human perception of visual realism and use that information to create an automated assessment of visual realism.
