ArticleJournal of personality and social psychology2018
Deep neural networks are more accurate than humans at detecting sexual orientation from facial images.
Article in Journal of personality and social psychology, 2018. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 65 papers, 3 of them syntheses that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
65 citing papers in PubMed, 3 syntheses or guidelines pooled it.
- Context-Contingent Privacy Concerns and Exploration of the Privacy Paradox in the Age of AI, Augmented Reality, Big Data, and the Internet of Things: Systematic Review.Journal of medical Internet research · 2025Pooled it
- Artificial Intelligence Crime: An Interdisciplinary Analysis of Foreseeable Threats and Solutions.Science and engineering ethics · 2020Pooled it
- Pooled it
- Human enhancement, past and present.Monash bioethics review · 2026Article
- The Israeli Face Database (IFD): A multi-ethnic database of faces with supporting social norming data.Behavior research methods · 2025Article
- Character and Personality Perception and Social Trait Judgment After Facial Surgical and Medical Aesthetic Interventions.Plastic and reconstructive surgery. Global open · 2025Article
- Is Generative AI Increasing the Risk for Technology-Mediated Trauma Among Vulnerable Populations?Nursing inquiry · 2025Article
- Utilizing large language models for gastroenterology research: a conceptual framework.Therapeutic advances in gastroenterology · 2025Review
- Beyond no harm: Advancing research on artificial intelligence for sexual and reproductive health and rights.npj women's health · 2025Article
- The Role of Dietary Antioxidants, Food Supplements and Functional Foods for Energy Enhancement in Healthcare Professionals.Antioxidants (Basel, Switzerland) · 2024Review
- The reanimation of pseudoscience in machine learning and its ethical repercussions.Patterns (New York, N.Y.) · 2024Review
- Smile variation leaks personality and increases the accuracy of interpersonal judgments.PNAS nexus · 2024Article
- Representativeness and face-ism: Gender bias in image search.New media & society · 2024Article
- Large language models know how the personality of public figures is perceived by the general public.Scientific reports · 2024Article
- The effect of sexual orientation on voice acoustic properties.Frontiers in psychology · 2024Article
- A megastudy on the predictability of personal information from facial images: Disentangling demographic and non-demographic signals.Scientific reports · 2023Article
- Human intuition as a defense against attribute inference.Scientific reports · 2023Article
- Using deep learning to predict ideology from facial photographs: expressions, beauty, and extra-facial information.Scientific reports · 2023Article
- The Group Right to Mutual Privacy.Digital society : ethics, socio-legal and governance of digital technology · 2023Article
- Unconscious Other's Impression Changer: A Method to Manipulate Cognitive Biases That Subtly Change Others' Impressions Positively/Negatively by Making AI Bias in Emotion Estimation AI.Sensors (Basel, Switzerland) · 2022Article
5 more citing papers are in PubMed but not listed here.
Corrections and comments
- Commented on by
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
We show that faces contain much more information about sexual orientation than can be perceived or interpreted by the human brain. We used deep neural networks to extract features from 35,326 facial images. These features were entered into a logistic regression aimed at classifying sexual orientation. Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 71% of cases for women. Human judges achieved much lower accuracy: 61% for men and 54% for women. The accuracy of the algorithm increased to 91% and 83%, respectively, given five facial images per person. Facial features employed by the classifier included both fixed (e.g., nose shape) and transient facial features (e.g., grooming style). Consistent with the prenatal hormone theory of sexual orientation, gay men and women tended to have gender-atypical facial morphology, expression, and grooming styles. Prediction models aimed at gender alone allowed for detecting gay males with 57% accuracy and gay females with 58% accuracy. Those findings advance our understanding of the origins of sexual orientation and the limits of human perception. Additionally, given that companies and governments are increasingly using computer vision algorithms to detect people's intimate traits, our findings expose a threat to the privacy and safety of gay men and women. (PsycINFO Database Record
Indexed as
Identifiers
29389215What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.