deepfake detection
Deepfake detection involves identifying synthetic media created using deep learning techniques that manipulate images or videos to portray people doing or saying things they did not actually do. Robust detection methods are crucial for combating misinformation and preserving digital integrity.
- $\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
- Fair Deepfake Detectors Can Generalize
- ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
- From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes
- Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
- Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
- The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction
- Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions
- VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models