Program

Deep Learning Multimedia Forensics. Combating fake media and misinformation. 

The Workshop will be held in Room 2i (for the venue details check the conference program https://2023.ecmlpkdd.org/attending/venues-and-participation/)

9-9.15

Title: Adversarial Magnification to Deceive Deepfake Detection through Super Resolution 

Authors: Davide Alessandro Coccomini (CNR-ISTI)*; Roberto Caldelli (CNIT, National Interuniversity Consortium for Telecommunications and Universitas Mercatorum); Giuseppe Amato (CNR-ISTI); Fabrizio Falchi (CNR-ISTI); Claudio Gennaro (CNR-ISTI)

5’ Q&A Session

9.20-9.35

Title: Improving Tiled Evolutionary Adversarial Attack

Authors: Vera Cervickova (Charles University, Faculty of Mathematics and Physics)*; Martin Pilát (Charles University, Faculty of Mathematics and Physics)

5’ Q&A Session

            9.40-9.55

Title: Tracing Videos to their Social Network with Robust DCT Analysis

Authors: Ben J Lewis (University of Warwick)*; Victor Sanchez (University of Warwick)

5’ Q&A Session

         10-10.50 Keynote Talk 

         Title: Deep Learning for Image and Video Forensics: Mine of Information or Minefield?

Presenter: Martino Jeriam, Amped Software, CEO and Founder

10’ Q&A Session

11.00-11.30 Coffee Break ☕

Ongoing Works Talk

11.35-11.40 

Title: Face Synthesis Detection

Speaker: Roberto Leyva Fernandez (University of Warwick)

11.40-11.45

Title:“Towards automated security and risk assessment of remote identity proofing procedures”. 

Speaker:Cecilia Pasquini (Fondazione Bruno Kessler)

11.45-11.50

Title: Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It

Speaker: Federico Siciliano (Sapienza University of Rome)

10’ Q&A Session on the Ongoing Works Talks

12.00-12.15

Title: DivNoise: A Data Collection for Source Identification on Diverse Camera Sensors

Authors:  Alberto Casagrande (University of Trento); Alessio Belli (University of Trento); Cecilia Pasquini (Fondazione Bruno Kessler); Duc-Tien Dang-Nguyen (University of Bergen)*

5’ Q&A Session

12.20-12.35

Title: Detecting Face Synthesis Using a Concealed Fusion Model

Authors: Roberto Leyva Fernandez (University of Warwick)*; Victor Sanchez (University of Warwick); Gregory Epiphaniou (University of Warwick); Carsten Maple (University of Warwick)

5’ Q&A Session

12.40-12.55

Title: All-for-One and One-For-All: Deep learning-based feature fusion for Synthetic Speech Detection

Authors: Daniele Mari (Università degli studi di Padova)*; Davide Salvi (Politecnico di Milano); Paolo Bestagini (Politecnico di Milano); Simone Milani (University of Padova)

5’ Q&A Session

13.00 Workshop Closing Conclusion and Remarks