16 papers
HexMIL: Hierarchical Attention MIL for Ante-Hoc Explainable Detection of AI-Manipulated CT Volumes
Orazio Pontorno, Luca Guarnera, Zahid Akhtar +1
The emergence of medical deepfakes, i.e., medical images manipulated by deep generative models, poses a significant threat to clinical workflows. However, existing detectors suffer…
The K-Space Signature: Frequency-Domain Representation Learning for Medical Deepfake Detection
Riccardo Raciti, Francesco Guarnera, Francesco Rundo +2
In medical imaging, generative models are increasingly deployed to synthesize realistic data and augment limited datasets. Unfortunately, while beneficial for privacy-preserving da…
Fraud is Not Just Rarity: A Causal Prototype Attention Approach to Realistic Synthetic Oversampling
Claudio Giusti, Luca Guarnera, Mirko Casu +1
Detecting fraudulent credit card transactions remains a significant challenge, due to the extreme class imbalance in real-world data and the often subtle patterns that separate fra…
Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
Orazio Pontorno, Mattia Litrico, Luca Guarnera +2
Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy and security. To ensure real-…
Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery
Claudio Giusti, Luca Guarnera, Sebastiano Battiato
The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern comput…
SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
Roberto Leotta, Salvatore Alfio Sambataro, Claudio Vittorio Ragaglia +5
Modern T2V/I2V generators synthesize people increasingly hard to distinguish from authentic footage, while current evaluation suites lag: legacy benchmarks target manipulation-base…