4 citations · 17 across the 27 of their papers we have counts for
32 papers
MOTIF: Person-of-Interest Deepfake Detection Beyond 3DMM Coefficients
Giovanni Affatato, Sara Mandelli, Paolo Bestagini +1
Video deepfakes targeting a specific individual, the Person-of-Interest (POI), are the most harmful ones, and, since a public figure is abundantly recorded, a detector can be built…
Synthetic Speech Attribution via Prototypical Networks
Viola Negroni, Paolo Bestagini, Stefano Tubaro
Synthetic speech attribution aims to identify the generative system responsible for a speech signal, but current approaches typically rely on black-box neural networks that provide…
Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores
Viola Negroni, Xin Wang, Wanying Ge +3
In this work, we propose an interpretable framework for speech deepfake detection based on artifact-specific expert models. Rather than relying on black-box decisions, the framewor…
CUPID: Reconstructing UV Texture Maps for Interpretable Person-of-Interest Deepfake Detection
Giovanni Affatato, Sara Mandelli, Edoardo Daniele Cannas +2
Deepfakes targeting a high-profile individual, known as Person-of-Interest (POI), are a threat to modern democracies and societies. Current POI deepfake detection methods still str…
Multi-Task Transformer for Explainable Speech Deepfake Detection via Formant Modeling
Viola Negroni, Luca Cuccovillo, Paolo Bestagini +2
In this work, we introduce a multi-task transformer for speech deepfake detection, capable of predicting formant trajectories and voicing patterns over time, ultimately classifying…
Enhanced Water Leak Detection with Convolutional Neural Networks and One-Class Support Vector Machine
Daniele Ugo Leonzio, Paolo Bestagini, Marco Marcon +1
Water is a critical resource that must be managed efficiently. However, a substantial amount of water is lost each year due to leaks in Water Distribution Networks (WDNs). This und…
Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection
Sara Mandelli, Diego Vila-Portela, David Vázquez-Padín +2
Over the years, the forensics community has proposed several deep learning-based detectors to mitigate the risks of generative AI. Recently, frequency-domain artifacts (particularl…
Forensic Similarity for Speech Deepfakes
Viola Negroni, Davide Salvi, Daniele Ugo Leonzio +2
In this paper, we introduce the concept of forensic similarity in the speech deepfake detection domain, which aims to determine whether two audio segments share the same underlying…
Attention-based Mixture of Experts for Robust Speech Deepfake Detection
Viola Negroni, Davide Salvi, Alessandro Ilic Mezza +2
AI-generated speech is becoming increasingly used in everyday life, powering virtual assistants, accessibility tools, and other applications. However, it is also being exploited fo…
Mitigating data replication in text-to-audio generative diffusion models through anti-memorization guidance
Francisco Messina, Francesca Ronchini, Luca Comanducci +2
A persistent challenge in generative audio models is data replication, where the model unintentionally generates parts of its training data during inference. In this work, we addre…
Phoneme-Level Analysis for Person-of-Interest Speech Deepfake Detection
Davide Salvi, Viola Negroni, Sara Mandelli +2
Recent advances in generative AI have made the creation of speech deepfakes widely accessible, posing serious challenges to digital trust. To counter this, various speech deepfake…
Source Verification for Speech Deepfakes
Viola Negroni, Davide Salvi, Paolo Bestagini +1
With the proliferation of speech deepfake generators, it becomes crucial not only to assess the authenticity of synthetic audio but also to trace its origin. While source attributi…
WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution
Pietro Bongini, Sara Mandelli, Andrea Montibeller +14
Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available gener…
Leveraging Land Cover Priors for Isoprene Emission Super-Resolution
Christopher Ummerle, Antonio Giganti, Sara Mandelli +2
Remote sensing plays a crucial role in monitoring Earth's ecosystems, yet satellite-derived data often suffer from limited spatial resolution, restricting their applicability in at…
Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching
Emma Coletta, Davide Salvi, Viola Negroni +2
The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising c…
Is JPEG AI going to change image forensics?
Edoardo Daniele Cannas, Sara Mandelli, Nataša Popović +4
In this paper, we investigate the counter-forensic effects of the new JPEG AI standard based on neural image compression, focusing on two critical areas: deepfake image detection a…
Comparative Analysis of ASR Methods for Speech Deepfake Detection
Davide Salvi, Amit Kumar Singh Yadav, Kratika Bhagtani +3
Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have pr…
POLIPHONE: A Dataset for Smartphone Model Identification from Audio Recordings
Davide Salvi, Daniele Ugo Leonzio, Antonio Giganti +4
When dealing with multimedia data, source attribution is a key challenge from a forensic perspective. This task aims to determine how a given content was captured, providing valuab…
Explainable Artifacts for Synthetic Western Blot Source Attribution
João Phillipe Cardenuto, Sara Mandelli, Daniel Moreira +3
Recent advancements in artificial intelligence have enabled generative models to produce synthetic scientific images that are indistinguishable from pristine ones, posing a challen…
DiffSSD: A Diffusion-Based Dataset For Speech Forensics
Kratika Bhagtani, Amit Kumar Singh Yadav, Paolo Bestagini +1
Diffusion-based speech generators are ubiquitous. These methods can generate very high quality synthetic speech and several recent incidents report their malicious use. To counter…
Freeze and Learn: Continual Learning with Selective Freezing for Speech Deepfake Detection
Davide Salvi, Viola Negroni, Luca Bondi +2
In speech deepfake detection, one of the critical aspects is developing detectors able to generalize on unseen data and distinguish fake signals across different datasets. Common a…
FakeMusicCaps: a Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models
Luca Comanducci, Paolo Bestagini, Stefano Tubaro
Text-To-Music (TTM) models have recently revolutionized the automatic music generation research field. Specifically, by reaching superior performances to all previous state-of-the-…
Leveraging Mixture of Experts for Improved Speech Deepfake Detection
Viola Negroni, Davide Salvi, Alessandro Ilic Mezza +2
Speech deepfakes pose a significant threat to personal security and content authenticity. Several detectors have been proposed in the literature, and one of the primary challenges…
Localization of Synthetic Manipulations in Western Blot Images
Anmol Manjunath, Viola Negroni, Sara Mandelli +2
Recent breakthroughs in deep learning and generative systems have significantly fostered the creation of synthetic media, as well as the local alteration of real content via the in…