Listing out research papers here for reading. Overtime I'll probably organize them with summaries, not sure if that will ever materialize though.
=====================================================
- FaceForensics++: Learning to Detect Manipulated Facial Images
- Mesonet: A Compact Facial Video Forgery Detection Network
- Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos
- Deepfake Video Detection Using Recurrent Neural Networks
- Exposing DeepFake Videos By Detecting Face Warping Artifacts
- Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
- Detecting GAN-Generated Imagery Using Saturation Cues
- FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network
- FakeLocator: Robust Localization of GAN-Based Face Manipulations via Semantic Segmentation Networks with Bells and Whistles
- Deep Fake Image Detection Based on Pairwise Learning
- Attention-Based Face AntiSpoofing of RGB Images, using a Minimal End-2-End Neural Network
- Deepfake Video Detection through Optical Flow based CNN
- ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
- Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos
- Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations
- DeepFake Detection Based on Discrepancies Between Faces and their Context
- Detection of Deepfakes Using Visual Artifacts and Neural Network Classifier
- Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder
- Spatio-temporal Features for Generalized Detection of Deepfake Videos
- Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
- SIAMESE NETWORK-BASED MULTI-MODAL DEEPFAKE DETECTION
- DeepFake Video Detection: A Time‑Distributed Approach
- SDHF: Spotting DeepFakes with Hierarchical Features
- Exploiting Prediction Error Inconsistencies through LSTM-based Classifiers to Detect Deepfake Videos
- NoiseScope: Detecting Deepfake Images in a Blind Setting
- Investigating the Impact of Pre-processing and Prediction Aggregation on the DeepFake Detection Task
- ID-Reveal: Identity-aware DeepFake Video Detection
- Identity-Driven DeepFake Detection
- Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
- EXPOSING GAN-GENERATED FACES USING INCONSISTENT CORNEAL SPECULAR HIGHLIGHTS
- Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks
- Cost Sensitive Optimization of Deepfake Detector
- Deepfake Detection Based on No-Reference Image Quality Assessment (NR-IQA)
=====================================================
- In ictu oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
- FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
- Protecting World Leaders Against Deepfakes
- Detecting Deep-Fake Videos From Phoneme-Viseme Mismatches
- Detecting Deep-Fake Videos from Appearance and Behavior
- Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking
======================================================