skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Exposing GAN-Generated Faces Using Inconsistent Corneal Specular Highlights
Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models. We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN synthesized faces.  more » « less
Award ID(s):
1822190
PAR ID:
10274525
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Page Range / eLocation ID:
2500 to 2504
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, IEEE)
    Facial Recognition Systems (FRS) have become one of the most viable biometric identity authentication approaches in supervised and unsupervised applications. However, FRSs are known to be vulnerable to adversarial attacks such as identity theft and presentation attacks. The master face dictionary attacks (MFDA) leveraging multiple enrolled face templates have posed a notable threat to FRS. Federated learning-based FRS deployed on edge or mobile devices are particularly vulnerable to MFDA due to the absence of robust MF detectors. To mitigate the MFDA risks, we propose a trustworthy authentication system against visual MFDA (Trauma). Trauma leverages the analysis of specular highlights on diverse facial components and physiological characteristics inherent to human faces, exploiting the inability of existing MFDAs to replicate reflective elements accurately. We have developed a feature extractor network that employs a lightweight and low-latency vision transformer architecture to discern inconsistencies among specular highlights and physiological features in facial imagery. Extensive experimentation has been conducted to assess Trauma’s efficacy, utilizing public GAN-face detection datasets and mobile devices. Empirical findings demonstrate that Trauma achieves high detection accuracy, ranging from 97.83% to 99.56%, coupled with rapid detection speeds (less than 11 ms on mobile devices), even when confronted with state-of-the-art MFDA techniques. 
    more » « less
  2. ; ; ; (, Novel Keratoconus Detection Method Using Smartphone)
    Keratoconus is a progressive corneal disease which may cause blindness if it is not detected in the early stage. In this paper, we propose a portable, low-cost, and robust keratoconus detection method which is based on smartphone camera images. A gadget has been designed and manufactured using 3-D printing to supplement keratoconus detection. A smartphone camera with the gadget provides more accurate and robust keratoconus detection performance. We adopted the Prewitt operator for edge detection and the support vector machine (SVM) to classify keratoconus eyes from healthy eyes. Experimental results show that the proposed method can detect mild, moderate, advanced, and severe stages of keratoconus with 89% accuracy on average. 
    more » « less
  3. ; ; (, Springer)
    Automatedanalysisofopticalcolonoscopy(OC)videoframes (to assist endoscopists during OC) is challenging due to variations in color, lighting, texture, and specular reflections. Previous methods ei- ther remove some of these variations via preprocessing (making pipelines cumbersome) or add diverse training data with annotations (but expen- sive and time-consuming). We present CLTS-GAN, a new deep learning model that gives fine control over color, lighting, texture, and specular reflection synthesis for OC video frames. We show that adding these colonoscopy-specific augmentations to the training data can improve state-of-the-art polyp detection/segmentation methods as well as drive next generation of OC simulators for training medical students. The code and pre-trained models for CLTS-GAN are available on Computational Endoscopy Platform GitHub (https://github.com/nadeemlab/CEP). 
    more » « less
  4. ; ; ; ; ; ; ; ; ; ; et al (, Nature Communications)
    Abstract Electroretinogram examinations serve as routine clinical procedures in ophthalmology for the diagnosis and management of many ocular diseases. However, the rigid form factor of current corneal sensors produces a mismatch with the soft, curvilinear, and exceptionally sensitive human cornea, which typically requires the use of topical anesthesia and a speculum for pain management and safety. Here we report a design of an all-printed stretchable corneal sensor built on commercially-available disposable soft contact lenses that can intimately and non-invasively interface with the corneal surface of human eyes. The corneal sensor is integrated with soft contact lenses via an electrochemical anchoring mechanism in a seamless manner that ensures its mechanical and chemical reliability. Thus, the resulting device enables the high-fidelity recording of full-field electroretinogram signals in human eyes without the need of topical anesthesia or a speculum. The device, superior to clinical standards in terms of signal quality and comfortability, is expected to address unmet clinical needs in the field of ocular electrodiagnosis. 
    more » « less
  5. ; ; ; (, Proceedings of the Design Society)
    Generative Adversarial Networks (GANs) have shown stupendous power in generating realistic images to an extend that human eyes are not capable of recognizing them as synthesized. State-of-the-art GAN models are capable of generating realistic and high-quality images, which promise unprecedented opportunities for generating design concepts. Yet, the preliminary experiments reported in this paper shed light on a fundamental limitation of GANs for generative design: lack of novelty and diversity in generated samples. This article conducts a generative design study on a large-scale sneaker dataset based on StyleGAN, a state-of-the-art GAN architecture, to advance the understanding of the performance of these generative models in generating novel and diverse samples (i.e., sneaker images). The findings reveal that although StyleGAN can generate samples with quality and realism, the generated and style-mixed samples highly resemble the training dataset (i.e., existing sneakers). This article aims to provide future research directions and insights for the engineering design community to further realize the untapped potentials of GANs for generative design. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email