[HTML][HTML] On the generalization of deep learning models in video deepfake detection

DA Coccomini, R Caldelli, F Falchi, C Gennaro - Journal of Imaging, 2023 - mdpi.com
The increasing use of deep learning techniques to manipulate images and videos,
commonly referred to as “deepfakes”, is making it more challenging to differentiate between …

Detecting images generated by diffusers

DA Coccomini, A Esuli, F Falchi, C Gennaro… - PeerJ Computer …, 2024 - peerj.com
In recent years, the field of artificial intelligence has witnessed a remarkable surge in the
generation of synthetic images, driven by advancements in deep learning techniques. These …

MINTIME: multi-identity size-invariant video deepfake detection

DA Coccomini, GK Zilos, G Amato… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
In this paper, we present MINTIME, a video deepfake detection method that effectively
captures spatial and temporal inconsistencies in videos that depict multiple individuals and …

Deepfake detection and the impact of limited computing capabilities

P Cantero-Arjona, A Sánchez-Macián - arxiv preprint arxiv:2402.14825, 2024 - arxiv.org
The rapid development of technologies and artificial intelligence makes deepfakes an
increasingly sophisticated and challenging-to-identify technique. To ensure the accuracy of …

MAD'22 Workshop: Multimedia AI against Disinformation

B Ionescu, G Kordopatis-Zilos, A Popescu… - Proceedings of the …, 2022 - dl.acm.org
The verification of multimedia content posted online becomes increasingly challenging due
to recent advancements in synthetic media manipulation and generation. Moreover …

Exploring Strengths and Weaknesses of Super-Resolution Attack in Deepfake Detection

DA Coccomini, R Caldelli, F Falchi, C Gennaro… - arxiv preprint arxiv …, 2024 - arxiv.org
Image manipulation is rapidly evolving, allowing the creation of credible content that can be
used to bend reality. Although the results of deepfake detectors are promising, deepfakes …

Shai-am: a machine learning platform for investment strategies

J Kwak, J Ahn, J Lee, S Park - arxiv preprint arxiv:2207.00436, 2022 - arxiv.org
The finance industry has adopted machine learning (ML) as a form of quantitative research
to support better investment decisions, yet there are several challenges often overlooked in …

[PDF][PDF] Deepfakes und manipulierte Realitäten

M Karaboga, N Frei, M Puppis… - … für die Schweiz …, 2024 - publica-rest.fraunhofer.de
Deepfakes und manipulierte Realitäten Page 1 Murat Karaboga, Nula Frei, Manuel Puppis,
Daniel Vogler, Patric Raemy, Frank Ebbers, Greta Runge, Adrian Rauchfleisch, Gabriele de …

Adversarial Magnification to Deceive Deepfake Detection Through Super Resolution

DA Coccomini, R Caldelli, G Amato, F Falchi… - … Conference on Machine …, 2023 - Springer
Deepfake technology is rapidly advancing, posing significant challenges to the detection of
manipulated media content. Parallel to that, some adversarial attack techniques have been …

[책][B] Deepfakes und manipulierte Realitäten: Technologiefolgenabschätzung und Handlungsempfehlungen für die Schweiz

M Karaboga, N Frei, M Puppis, D Vogler, P Raemy… - 2024 - books.google.com
Desinformation, Identitätsmissbrauch, Facial Reenactment, Face Morphing, Face Swap**,
Gesichtsgeneration, Full Body Puppetry, Deepfake-Audio Die Imitation von Stimmen und …