# Are Detectors Fair to Indian IP-AIGC? A Cross-Generator Study

arXiv: https://arxiv.org/abs/2512.02850 · HTML: https://mlsanity.com/paper/2512.02850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection](https://mlsanity.com/paper/2307.01426/) (2023)
- [Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2411.15633/) (2024)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark](https://mlsanity.com/paper/2406.00783/) (2024)
- [Preserving AUC Fairness in Learning with Noisy Protected Groups](https://mlsanity.com/paper/2505.18532/) (2025)
- [InstaFace: Identity-Preserving Facial Editing with Single Image Inference](https://mlsanity.com/paper/2502.20577/) (2025)
- [Robust AI-Generated Face Detection with Imbalanced Data](https://mlsanity.com/paper/2505.02182/) (2025)
- [Hindi audio-video-Deepfake (HAV-DF): A Hindi language-based Audio-video Deepfake Dataset](https://mlsanity.com/paper/2411.15457/) (2024)

## Abstract (arXiv)

Modern image editors can produce identity-preserving AIGC (IP-AIGC), where the same person appears with new attire, background, or lighting. The robustness and fairness of current detectors in this regime remain unclear, especially for under-represented populations. We present what we believe is the first systematic study of IP-AIGC detection for Indian and South-Asian faces, quantifying cross-generator generalization and intra-population performance. We assemble Indian-focused training splits from FairFD and HAV-DF, and construct two held-out IP-AIGC test sets (HIDF-img-ip-genai and HIDF-vid-ip-genai) using commercial web-UI generators (Gemini and ChatGPT) with identity-preserving prompts. We evaluate two state-of-the-art detectors (AIDE and Effort) under pretrained (PT) and fine-tuned (FT) regimes and report AUC, AP, EER, and accuracy. Fine-tuning yields strong in-domain gains (for example, Effort AUC 0.739 to 0.944 on HAV-DF-test; AIDE EER 0.484 to 0.259), but consistently degrades performance on held-out IP-AIGC for Indian cohorts (for example, AIDE AUC 0.923 to 0.563 on HIDF-img-ip-genai; Effort 0.740 to 0.533), which indicates overfitting to training-generator cues. On non-IP HIDF images, PT performance remains high, which suggests a specific brittleness to identity-preserving edits rather than a generic distribution shift. Our study establishes IP-AIGC-Indian as a challenging and practically relevant scenario and motivates representation-preserving adaptation and India-aware benchmark curation to close generalization gaps in AIGC detection.