Cover Image

Beyond Performance Disparities: A Three-Level Audit of Representational Harm in CelebA

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Sieun, He, Yuanmo
Format:	Preprint
Published:	2026
Subjects:	Computers and Society Computer Vision and Pattern Recognition K.4
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Attention IoU: Examining Biases in CelebA using Attention Maps
by: Serianni, Aaron, et al.
Published: (2025)

Can Vision-Language Models Replace Human Annotators: A Case Study with CelebA Dataset
by: Lu, Haoming, et al.
Published: (2024)

Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AI
by: Mathys, Melanie, et al.
Published: (2024)

A Framework for Evaluating Vision-Language Model Safety: Building Trust in AI for Public Sector Applications
by: Rashid, Maisha Binte, et al.
Published: (2025)

Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping
by: Nwatu, Joan, et al.
Published: (2025)

From Vulnerable Data Subjects to Vulnerabilizing Data Practices: Navigating the Protection Paradox in AI-Based Analyses of Platformized Lives
by: Pandiani, Delfina S. Martinez, et al.
Published: (2026)

Synthetic Image Generation in Cyber Influence Operations: An Emergent Threat?
by: Mathys, Melanie, et al.
Published: (2024)

Lookism: The overlooked bias in computer vision
by: Gulati, Aditya, et al.
Published: (2024)

Deep Generative Attacks and Countermeasures for Data-Driven Offline Signature Verification
by: Ngo, An, et al.
Published: (2023)

Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper
by: Goree, Samuel, et al.
Published: (2022)

SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation
by: Yu, Sumin, et al.
Published: (2025)

Verifiable Provenance and Watermarking for Generative AI: An Evidentiary Framework for International Operational Law and Domestic Courts
by: Lundström-Imanov, Gustav Olaf Yunus Laitinen-Fredriksson, et al.
Published: (2026)

Experiments as Code: A Concept for Reproducible, Auditable, Debuggable, Reusable, & Scalable Experiments
by: Aguilar, Leonel, et al.
Published: (2022)

Towards an Automated Framework to Audit Youth Safety on TikTok
by: Xue, Linda, et al.
Published: (2025)

Prototype-Guided Concept Erasure in Diffusion Models
by: Cai, Yuze, et al.
Published: (2026)

Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection
by: Loth, Alexander, et al.
Published: (2026)

Impact of Blur and Resolution on Demographic Disparities in 1-to-Many Facial Identification
by: Bhatta, Aman, et al.
Published: (2023)

Toward Dignity-Aware AI: Next-Generation Elderly Monitoring from Fall Detection to ADL
by: Shao, Xun, et al.
Published: (2025)

Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models
by: Nwatu, Joan, et al.
Published: (2024)

Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI
by: Sun, Luhang, et al.
Published: (2023)

Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators
by: Jo, Claire Wonjeong, et al.
Published: (2024)

Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative Models
by: Mandal, Abhishek, et al.
Published: (2024)

LLeMpower: Understanding Disparities in the Control and Access of Large Language Models
by: Sathish, Vishwas, et al.
Published: (2024)

Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systems
by: Jaiswal, Siddharth D, et al.
Published: (2024)

Auditing the Compliance and Enforcement of Twitter's Advertising Policy
by: Vekaria, Yash, et al.
Published: (2023)

Seeking Help, Facing Harm: Auditing TikTok's Mental Health Recommendations
by: Jamie, Pooriya, et al.
Published: (2026)

Governed Auditable Decisioning Under Uncertainty: Synthesis and Agentic Extension
by: Solozobov, Oleg
Published: (2026)

Advancing 6D Pose Estimation in Augmented Reality -- Overcoming Projection Ambiguity with Uncontrolled Imagery
by: Manawadu, Mayura, et al.
Published: (2024)

Why AI Harms Can't Be Fixed One Identity at a Time: What 5300 Incident Reports Reveal About Intersectionality
by: Bogucka, Edyta, et al.
Published: (2026)

The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data
by: Teikari, Petteri, et al.
Published: (2025)

Performativity and Prospective Fairness
by: Zezulka, Sebastian, et al.
Published: (2023)

Keystroke Dynamics Against Academic Dishonesty in the Age of LLMs
by: Kundu, Debnath, et al.
Published: (2024)

The Necessity of AI Audit Standards Boards
by: Manheim, David, et al.
Published: (2024)

Beyond Explanation: Evidentiary Rights for Algorithmic Accountability
by: Stewart, Matthew
Published: (2026)

Aesthetics as Structural Harm: Algorithmic Lookism Across Text-to-Image Generation and Classification
by: Doh, Miriam, et al.
Published: (2026)

Rainbow Noise: Stress-Testing Multimodal Harmful-Meme Detectors on LGBTQ Content
by: Tong, Ran, et al.
Published: (2025)

Position: Age Estimation Models Do Not Process Biometric Data
by: Marshalkin, Nikita
Published: (2026)

Evaluating Performance Consistency in Competitive Programming: Educational Implications and Contest Design Insights
by: Luo, Zhongtang, et al.
Published: (2025)

Assessing the Auditability of AI-integrating Systems: A Framework and Learning Analytics Case Study
by: Fernsel, Linda, et al.
Published: (2024)

Understanding the Representation of Older Adults in Motion Capture Locomotion Datasets
by: Yu, Yunkai, et al.
Published: (2025)