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

Shen, Sijie; Furuta, Ryosuke; Yamasaki, Toshihiko; Aizawa, Kiyoharu

doi:10.1109/bigmm.2017.64

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5. Similarly, Shen et al [144] proposed two different techniques to generate adversarial examples for faces that can have high 'attractiveness scores' but low 'subjective scores' for the face attractiveness evaluation using deep neural network. We refer to [185] for further attacks related to the task of face recognition.…”

Section: Attacks On Face Attributesmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

Deep learning is at the heart of the current rise of artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

show abstract

Section: Attacks On Face Attributesmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

show abstract

“… 14 , 15 , 16 , 17 , 18 , 19 , 20 There have been reports on makeup, for example, facial attractiveness evaluation, automatic makeup generation, makeup pattern suggestion. 21 , 22 , 23 , 24 We hypothesized that deep learning technology could be used to obtain a makeup finish evaluation technology that can evaluate subtle textures as well as human visual evaluation.…”

Section: Introductionmentioning

confidence: 99%

Skin patch based makeup finish assessment technique by deep neural network

Nishino

2024

Skin Research and Technology

View full text Add to dashboard Cite

BackgroundSkin color and texture play a significant role in influencing impressions. To understand the influence of skin appearance and to develop better makeup products, objective evaluation methods for makeup finish have been explored. This study aims to apply machine learning technology, specifically deep neural network (DNN), to accurately analyze and evaluate delicate and complex cosmetic skin textures.Methods“Skin patch datasets” were extracted from facial images and used to train a DNN model. The advantages of using skin patches include retaining fine texture, eliminating false correlations from non‐skin features, and enabling visualization of the inferred results for the entire face. The DNN was trained in two ways: a classification task to classify skin attributes and a regression task to predict the visual assessment of experts. The trained DNNs were applied for the evaluation of actual makeup conditions.ResultsIn the classification task training, skin patch‐based classifiers for age range, presence or absence of base makeup, formulation type (powder/liquid) of the applied base makeup, and immediate/while after makeup application were developed. The trained DNNs on regression task showed high prediction accuracy for the experts’ visual assessment. Application of DNN to the evaluation of actual makeup conditions clearly showed appropriate evaluation results in line with the appearance of the makeup finish.ConclusionThe proposed method of using DNNs trained on skin patches effectively evaluates makeup finish. This approach has potential applications in visual science research and cosmetics development. Further studies can explore the analysis of different skin conditions and the development of personalized cosmetics.

show abstract

“…Besides, systems for detecting malicious information [39]- [41] are also under the threat of adversarial examples. Therefore, researchers have paid much attention to the security problem caused by adversarial examples [42], [43]. Numerous works study the adversarial attacks and defenses, aiming at exploring what adversarial examples are [12], [44]- [46], why they exist, how they infect the behavior of DNN models, and how to solve this security problem.…”

Section: Introductionmentioning

confidence: 99%

Towards a Robust Deep Neural Network in Texts: A Survey

Wang¹,

Wang²,

Wang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing). However, researches have shown that DNN models are vulnerable to adversarial examples, which cause incorrect predictions by adding imperceptible perturbations into normal inputs. Studies on adversarial examples in image domain have been well investigated, but in texts the research is not enough, let alone a comprehensive survey in this field. In this paper, we aim at presenting a comprehensive understanding of adversarial attacks and corresponding mitigation strategies in texts. Specifically, we first give a taxonomy of adversarial attacks and defenses in texts from the perspective of different natural language processing (NLP) tasks, and then introduce how to build a robust DNN model via testing and verification. Finally, we discuss the existing challenges of adversarial attacks and defenses in texts and present the future research directions in this emerging field.

show abstract

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

Cited by 11 publications

References 10 publications

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Skin patch based makeup finish assessment technique by deep neural network

Towards a Robust Deep Neural Network in Texts: A Survey

Contact Info

Product

Resources

About