secml-lab-vt/EvolvingThreat-DeepfakeImageDetect
Code and Datasets for the paper "An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape" [IEEE S&P, 2024]
This project helps security analysts, forensic investigators, or content moderators assess whether an image is a deepfake. It takes an image as input and applies various detection methods to determine its authenticity. The output is a classification indicating if the image is real or synthetically generated. This tool is intended for professionals who need to identify manipulated media.
No commits in the last 6 months.
Use this if you need to evaluate the effectiveness of different deepfake image detection techniques or analyze how deepfake generation methods evolve.
Not ideal if you need an out-of-the-box solution for casual deepfake detection, as it requires technical setup and understanding of research-oriented methodologies.
Stars
20
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/secml-lab-vt/EvolvingThreat-DeepfakeImageDetect"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation