Fooling Neural Networks in Face Attractiveness Evaluation: Adversarial Examples with High Attractiveness Score But Low Subjective Score

People are fond of taking and sharing photos in their social life, and a large part of it is face images, especially selfies. A lot of researchers are interested in analyzing attractiveness of face images. Benefited from deep neural networks (DNNs) and training data, researchers have been developing deep learning models that can evaluate facial attractiveness of photos. However, recent development on DNNs showed that they could be easily fooled even when they are trained on a large dataset. In this paper, we used two approaches to generate adversarial examples that have high attractiveness scores but low subjective scores for face attractiveness evaluation on DNNs. In the first approach, experimental results using the SCUT-FBP dataset showed that we could increase attractiveness score of 20 test images from 2.67 to 4.99 on average (score range: [1, 5]) without noticeably changing the images. In the second approach, we could generate similar images from noise image with any target attractiveness score. Results show by using this approach, a part of attractiveness information could be manipulated artificially.