IBI-001295 - Criticalpublie
Image Generation Bias
Biais de génération d'images
IBI Score
9.2
out of 10
Severity5_critique
Frequencysystematique
Scope groups5
Detection difficulty4
🇫🇷 Définition (FR)
Modèles génératifs d'images reproduisant des stéréotypes raciaux et de genre.
🇬🇧 Definition (EN)
Image generative models reproducing racial and gender stereotypes.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L2
Representation
S
Specific
S22
Linguistic bias
💡
Concrete Example
DALL-E génère systématiquement des CEO blancs et des assistants noirs pour les mêmes prompts.
📊 Detection Metrics
Demographic Parity DifferenceDisparate Impact RatioEqualized Odds Difference
⚙ Alert Thresholds
Disparate Impact Ratio0.8
Equalized Odds Difference0.1
Demographic Parity Difference0.1
📚 Sources & Scientific References
- •Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large ScaleFederico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan (2023)
- •
🛡 Impact & Mitigation
⚠ Documented evidence (Studies & Incidents)
- Google suspend la g�n�ration d'images de personnes de Gemini apr�s des images historiquement inexactes : Source : https://techcrunch.com/tag/google-gemini-image-generation-historical-people-inaccuracies/
Impact:
🎯 Vulnerable groups impacted
Black / Afro-descendantWomen
🛠 Mitigation methodologies
- DEMO_PARITY : Demographic Parity
- AUDIT_TIERS : Third-party Audit
🏢 Sectors concerned
Media & Social Platforms (Risk: /5)
⚖ Applicable regulations
🇪🇺 Europe
- •AI_ACT_10 : AI Act (UE) 2024/1689
🌍 International
- •ISO_42001 : ISO/IEC 42001:2023
- •UNESCO_2021 : UNESCO - Recommandation sur l'éthique de l'IA
- •OECD_AI_PRINCIPLES : OCDE - Principes IA
- •COE_AI_CONVENTION_INT : Conseil de l'Europe - Convention IA
📋 Metadata
Contributor
Mohamadou SIDIBE
Institution
AI BIAIS INITIATIVE
Version
1
Created on
October 14, 2026
Updated on
November 4, 2026
UUID
eb3b0f54-8a3a-49be-a839-c33a46badb15
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.