ML Security PapersTowards Generalizable Deepfake Image Detection with Vision Transformers
Kaliki V Srinanda , M Manvith Prabhu , Hemanth K Mogilipalem , Jayavarapu S Abhinai , Vaibhav Santhosh , Aryan Herur , Deepu Vijayasenan
Published on arXiv
2604.17376
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
Achieves 96.77% AUC and 9% EER on DF-Wild test set, beating state-of-the-art Effort algorithm by 7.05% AUC and 8% EER
Vision Transformer Ensemble for Deepfake Detection
Novel technique introduced
In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods. In this paper, we use an ensemble of fine-tuned vision transformers like DINOv2, AIMv2 and OpenCLIP's ViT-L/14 to create generalizable method to detect deepfakes. We use the DF-Wild dataset released as part of the IEEE SP Cup 2025, because it uses a challenging and diverse set of manipulations and generation techniques. We started our experiments with CNN classifiers trained on spatial features. Experimental results show that our ensemble outperforms individual models and strong CNN baselines, achieving an AUC of 96.77% and an Equal Error Rate (EER) of just 9% on the DF-Wild test set, beating the state-of-the-art deepfake detection algorithm Effort by 7.05% and 8% in AUC and EER respectively. This was the winning solution for SP Cup, presented at ICASSP 2025.
Key Contributions
- Ensemble of fine-tuned vision transformers (DINOv2, AIMv2, OpenCLIP ViT-L/14) for generalizable deepfake detection
- Achieves 96.77% AUC and 9% EER on DF-Wild test set, outperforming state-of-the-art by 7.05% AUC
- Winning solution for IEEE SP Cup 2025 deepfake detection challenge
🛡️ Threat Analysis
Core contribution is detecting AI-generated and manipulated facial images (deepfakes) — this is AI-generated content detection and output integrity verification.