# ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection Source: [ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:41.143Z Authors: Davide Cozzolino, Justus Thies, Andreas R\\"ossler, Christian Riess, Matthias Nie{\\ss}ner, Luisa Verdoliva Published: 2018-12-06T13:11:09.000Z ## 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%. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Facial Forgery Detection on FaceForensics++ Hidden Benchmark low quality (test)](): Facial Forgery Detection; FaceForensics++ Hidden Benchmark low quality (test); Precision (DF): 85.45. - [Image Manipulation Detection on GauGAN COCO (test)](): Image Manipulation Detection; GauGAN COCO (test); AP (%): 83.3. - [Image Manipulation Detection on StarGAN CelebA-HQ (test)](): Image Manipulation Detection; StarGAN CelebA-HQ (test); AP: 91.7. - [Image Manipulation Detection on CycleGAN Facades (test)](): Image Manipulation Detection; CycleGAN Facades (test); AP (%): 77.2. ## Original sources and implementation [Original paper]() [PDF]()