REVIEW 7 cited by
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Distinguishing manipulated from real images is becoming increasingly difficult as new sophisticated image forgery approaches come out by the day. Naive classification approaches based on Convolutional Neural Networks (CNNs) show excellent performance in detecting image manipulations when they are trained on a specific forgery method. However, on examples from unseen manipulation approaches, their performance drops significantly. To address this limitation in transferability, we introduce Forensic-Transfer (FT). We devise a learning-based forensic detector which adapts well to new domains, i.e., novel manipulation methods and can handle scenarios where only a handful of fake examples are available during training. To this end, we learn a forensic embedding based on a novel autoencoder-based architecture that can be used to distinguish between real and fake imagery. The learned embedding acts as a form of anomaly detector; namely, an image manipulated from an unseen method will be detected as fake provided it maps sufficiently far away from the cluster of real images. Comparing to prior works, FT shows significant improvements in transferability, which we demonstrate in a series of experiments on cutting-edge benchmarks. For instance, on unseen examples, we achieve up to 85% in terms of accuracy, and with only a handful of seen examples, our performance already reaches around 95%.
Forward citations
Cited by 7 Pith papers
-
Practical Manipulation Model for Robust Deepfake Detection
A data-augmentation method for deepfake detection that adds diverse pseudo-fakes and strong degradations during training, increasing robustness and low-quality benchmark AUC at a slight cost on clean high-quality data.
-
InfoDense: Density-Aware Regional Decisive Replay for Memory-Efficient Incremental Face Forgery Detection
InfoDense replays only density-ranked, forgery-decisive face fragments rather than full images, cutting memory use and improving incremental deepfake detection.
-
Perceptual Classifiers: Detecting Generative Images using Perceptual Features
A two-layer classifier trained on CONTRIQUE image-quality features achieves state-of-the-art accuracy on GenImage and DRCT-2M fake-image detection benchmarks.
-
Towards Open-world Generalized Deepfake Detection: General Feature Extraction via Unsupervised Domain Adaptation
A training strategy (OWG-DS) combines domain distance optimization, similarity-based class separation, and adversarial domain classification to adapt deepfake detectors to new forgery types with limited labeled and ab...
-
Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content
A masked-region recovery score, computed with an open-source surrogate fine-tuned on under 1,000 target samples, separates images generated by a black-box diffusion model from real photos.
-
Face Deepfakes -- A Comprehensive Review
A review of face deepfake generation and detection finds that off-the-shelf deepfake tools such as Wav2Lip and SimSwap achieve high attack success rates against lightweight face recognition models.
-
Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image Detection
Randomly masking 60 to 80 percent of input patches while fine-tuning a pre-trained CLIP-ResNet50 produces a detector that reaches 92.7% average accuracy on GenImage with 1% training data, outperforming the prior state...
Discussion (0). Continue with ORCID to comment.