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: Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation
Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports suggest that these systems may produce biased results, discriminating against people in certain demographic groups. Diagnosing and understanding the underlying true causes of model biases, however, are challenging tasks because modern computer vision systems rely on complex black-box models whose behaviors are hard to decode. We propose to use an encoder-decoder network developed for image attribute manipulation to synthesize facial images varying in the dimensions of gender and race while keeping other signals intact. We use these synthesized images to measure counterfactual fairness of commercial computer vision classifiers by examining the degree to which these classifiers are affected by gender and racial cues controlled in the images, e.g., feminine faces may elicit higher scores for the concept of nurse and lower scores for STEM-related concepts.  more » « less
Award ID(s):
1831848
PAR ID:
10299105
Author(s) / Creator(s):
;
Date Published:
Journal Name:
FATE/MM '20: Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia
Page Range / eLocation ID:
1 to 5
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV))
    null (Ed.)
    Existing public face image datasets are strongly biased toward Caucasian faces, and other races (e.g., Latino) are significantly underrepresented. The models trained from such datasets suffer from inconsistent classification accuracy, which limits the applicability of face analytic systems to non-White race groups. To mitigate the race bias problem in these datasets, we constructed a novel face image dataset containing 108,501 images which is balanced on race. We define 7 race groups: White, Black, Indian, East Asian, Southeast Asian, Middle Eastern, and Latino. Images were collected from the YFCC-100M Flickr dataset and labeled with race, gender, and age groups. Evaluations were performed on existing face attribute datasets as well as novel image datasets to measure the generalization performance. We find that the model trained from our dataset is substantially more accurate on novel datasets and the accuracy is consistent across race and gender groups. We also compare several commercial computer vision APIs and report their balanced accuracy across gender, race, and age groups. Our code, data, and models are available at https://github.com/joojs/fairface. 
    more » « less
  2. ; (, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V)
    Solomon, Latasha; Schwartz, Peter J. (Ed.)
    In recent years, computer vision has made significant strides in enabling machines to perform a wide range of tasks, from image classification and segmentation to image generation and video analysis. It is a rapidly evolving field that aims to enable machines to interpret and understand visual information from the environment. One key task in computer vision is image classification, where algorithms identify and categorize objects in images based on their visual features. Image classification has a wide range of applications, from image search and recommendation systems to autonomous driving and medical diagnosis. However, recent research has highlighted the presence of bias in image classification algorithms, particularly with respect to human-sensitive attributes such as gender, race, and ethnicity. Some examples are computer programmers being predicted better in the context of men in images compared to women, and the accuracy of the algorithm being better on greyscale images compared to colored images. This discrepancy in identifying objects is developed through correlation the algorithm learns from the objects in context known as contextual bias. This bias can result in inaccurate decisions, with potential consequences in areas such as hiring, healthcare, and security. In this paper, we conduct an empirical study to investigate bias in the image classification domain based on sensitive attribute gender using deep convolutional neural networks (CNN) through transfer learning and minimize bias within the image context using data augmentation to improve overall model performance. In addition, cross-data generalization experiments are conducted to evaluate model robustness across popular open-source image datasets. 
    more » « less
  3. ; ; ; ; (, Proceedings of the National Academy of Sciences)
    Researchers in the social sciences are interested in the consequences of institutions, increasingly on a global scale. Institutions that may be negotiated between states can have consequences at a microlevel, as local populations adjust their expectations and ultimately even their behavior to take institutional rules into account. However, large-scale fine-grained analyses that test for the complex evidence of such institutions locally are rare. This article focuses on a key institution: International borders. Using computer vision techniques, we show that it is possible to produce a geographically specific, validated, and replicable way to characterizeborder legibility, by which we mean the ability to visually detect the presence of an international border in physical space. We develop and compare computer vision techniques to automatically estimate legibility scores for 627,656 imagery tiles from virtually every border in the world. We evaluate statistical and data-driven computer vision methods, finding that fine-tuning pretrained visual recognition models on a small set of human judgments allows us to produce local legibility scores globally that align well with human notions of legibility. Finally, we interpret these scores as useful approximations of states’ border orientations, a concept that prior literature has used to capture the visible investments states make in border areas to maintain jurisdictional authority territorially. We validate our measurement strategy using both human judgments and five nomological validation indicators. 
    more » « less
  4. ; ; ; (, IEEE Symposium Series on Computational Intelligence (SSCI))
    The prevalent commercial deployment of automated facial analysis systems such as face recognition as a robust authentication method has increasingly fueled scientific attention. Current machine learning algorithms allow for a relatively reliable detection, recognition, and categorization of face images comprised of age, race, and gender. Algorithms with such biased data are bound to produce skewed results. It leads to a significant decrease in the performance of state-of-the-art models when applied to images of gender or ethnicity groups. In this paper, we study the gender bias in facial recognition with gender balanced and imbalanced training sets using five traditional machine learning algorithms. We aim to report the machine learning classifiers which are inclined towards gender bias and the ones which mitigate it. Miss rates metric is effective in finding out potential bias in predictions. Our study utilizes miss rates metric along with a standard metric such as accuracy, precision or recall to evaluate possible gender bias effectively. 
    more » « less
  5. ; (, IEEE International Symposium on Signal Processing and Information Technology)
    Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and ex- tensive popularity, they are not without their exploitable flaws. Initially applied to computer vision systems, the generation of adversarial examples is a process in which seemingly imper- ceptible perturbations are made to an image, with the purpose of inducing a deep learning based classifier to misclassify the image. Due to recent trends in speech processing, this has become a noticeable issue in speech recognition models. In late 2017, an attack was shown to be quite effective against the Speech Commands classification model. Limited-vocabulary speech classifiers, such as the Speech Commands model, are used quite frequently in a variety of applications, particularly in managing automated attendants in telephony contexts. As such, adversarial examples produced by this attack could have real-world consequences. While previous work in defending against these adversarial examples has investigated using audio preprocessing to reduce or distort adversarial noise, this work explores the idea of flooding particular frequency bands of an audio signal with random noise in order to detect adversarial examples. This technique of flooding, which does not require retraining or modifying the model, is inspired by work done in computer vision and builds on the idea that speech classifiers are relatively robust to natural noise. A combined defense incorporating 5 different frequency bands for flooding the signal with noise outperformed other existing defenses in the audio space, detecting adversarial examples with 91.8% precision and 93.5% recall. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email