Detection of fake news on Social Media platforms: project

Learn more

About DISSIMILAR

Short description of the project's goals

Research Team

Description of involved researchers

Achievements

Publications, presentations, and dissemination activities

In media

Press releases about DISSIMILAR

About DISSIMILAR project

Detection of fake newS on SocIal MedIa pLAtfoRms (DISSIMILAR) is a project within CONCERT-Japan (Connecting and Coordinating European Research and Techology Development with Japan) programme and 7th Joint Call on "ICT for Resilient, Safe and Secure Society" which is realized by the consortium consisting of researchers from: Fundació per a la Universitat Oberta de Catalunya (Spain), Okayama University (Japan), and Warsaw University of Technology (Poland). The project will be realized between June 2021 and May 2024. The funding is provided through grants number PCI2020-120689-2 (Spanish Government), JPMJSC20C3 (Japanese Government), and EIG CONCERT-JAPAN/05/2021 (National Centre for Research and Development, Poland):

Digital media have changed the classical model of mass media that consider the emisor of a message and a passive receptor, to a model where users of the digital media are able appropriate the contents, recreate and circulate them. In this context, online social media are a suitable circuit for the distribution of fake news and the spread of desinformation. Particularly, photo and video editing tools and recent advances in artificial intelligence allow non-professionals to easily counterfeit multimedia documents and create deep fakes. To avoid the spread of disinformation, some online social media deploy methods to filter fake content. Although this can be an effective method, its centralized approach gives an enormous power to the manager of these services.

DISSIMILAR project aims to provide content creators with tools to watermark their creations and make any modification easily spottable. Also, this project will give online social media users tools based on state of the art signal processing and machine learning methods to detect fake content. The combination of the watermarking and detection tools will empower users to discern between original and fake multimedia content without the need for assessment and control from a centralized service. Furthermore, this project will be developed using a user centered design approach. To build the most effective tools and take into account the cultural dimension and the diversity of final users, this project will conduct a comprehensive user experience study. Finally, it is worth noting that the collaboration of the three partners from Japan, Poland and Spain is fundamental not only to complement their expertise and technical background but also to engage participants from different regions, cultural backgrounds and life trajectories in the user experience study that allows designing tools with an inclusive and global aim.


Fig. 1. Envisioned general DISSIMILAR architecture.

DISSIMILAR combines research on watermarking and machine learning with a user experience study to develop novel technological tools to help users to distinguish between original and altered media content. With the proposed tools we expect online social media users to be able to identify the authorship of a content to distinguish legitimate from fake multimedia content in an autonomous manner, without the need for the platform manager to control or validate any content. Furthermore, the watermarking tools will also provide content creators with a way to protect their creations against manipulation. Hence, the aim of this project is to provide user centric tools that combat disinformation and that contribute minimizing the redistribution of fake news in online social media.

Research Team

The consortium of the DISSIMILAR project consists of researchers from three institutions: Fundació per a la Universitat Oberta de Catalunya (Spain), Okayama University (Japan), and Warsaw University of Technology (Poland).



Fundació per a la Universitat Oberta de Catalunya (project leader for Europe):

  • David Megías Jiménez (leader of Spanish team)
  • Tanya Koohpayeharaghi
  • Helena Rifà Pous
  • Andrea Rosales
  • Julián Salas Piñón
  • Mireia Fernández-Ardèvol
  • Daniel Blanche-T.



Okayama / Tohoku University (project leader for Japan):

  • Minoru Kuribayashi (leader of Japanese team)
  • Tatsuya Yasui
  • Daichi Takeshita
  • Koki Nakai
  • Yuma Yamasaki
  • Kenta Tsunomori
  • Hiroto Takiwaki



Warsaw University of Technology (project partner):

  • Wojciech Mazurczyk (leader of Polish team)
  • Krzysztof Cabaj
  • Anna Visvizi
  • Agnieszka Malanowska
  • Marcin Kowalczyk
  • Piotr Nowakowski
  • Piotr Żórawski

Achievements

Publication of Books:

  1. D. Megias, W. Mazurczyk, M. Kuribayashi (Eds.), "Data Hiding and Its Applications: Digital Watermarking and Steganography", MDPI, DOI: 10.3390/books978-3-0365-2937-0, January 2022


Publication of Articles in Journals:

  1. A. Malanowska, W. Mazurczyk, T. Araghi, D. Megias, M. Kuribayashi, "Digital watermarking - a meta-survey and techniques for fake news detection," IEEE Access, 2024, pp. 1-35, DOI: 10.1109/ACCESS.2024.3374201
  2. W. Mazurczyk, D. Lee, A. Vlachos, "Disinformation 2.0 in the Age of AI: A Cybersecurity Perspective," Communications of the ACM, Volume 67, Issue 3, pp 36-39, DOI: 10.1145/3624721, March 2024
  3. R. Kozik, W. Mazurczyk, K. Cabaj, A. Pawlicka, M. Pawlicki, M. Choras, "Deep Learning for Combating Misinformation in Multicategorical Text Content," Sensors 2023, 23, 9666, DOI: 10.3390/s23249666
  4. J. N. Chaudhari, H. Galiyawala, M. Kuribayashi, P. Sharma, M. S. Raval, "Designing practical end-to-end system for soft biometric-based person retrieval from surveillance videos," IEEE Access, vol.11, pp.133640-133657, 2023. https://doi.org/10.1109/ACCESS.2023.3337108
  5. Araghi, T.K., D. Megias, "Analysis and effectiveness of deeper levels of SVD on performance of hybrid DWT and SVD watermarking," Multimedia Tools and Applications, 2023, DOI: 10.1007/s11042-023-15554-z
  6. R. Kozik, A. Pawlicka, M. Pawlicki, M. Choras, W. Mazurczyk and K. Cabaj, "A Meta-Analysis of State-of-the-Art Automated Fake News Detection Methods," in IEEE Transactions on Computational Social Systems, DOI: 10.1109/TCSS.2023.3296627
  7. M. Kuribayashi T. Yasui, A. Malik, "White box watermarking for convolution layers in fine-tuning model using the constant weight code," Journal of Imaging, vol.9, no.6, 117, 2023. DOI:10.3390/jimaging9060117
  8. M. T. Ahvanooey, X. Zhu, S. Ou, H. D. Mazraeh, W. Mazurczyk, K. R. Choo, C. Li, "AFPr-AM: A Novel Fuzzy-AHP based Privacy Risk Assessment Model For Strategic Information Management of Social Media Platforms", Computers & Security, Volume 130, July 2023, 103263
  9. A. Qureshi, D. Megias, "Blockchain-Based Multimedia Content Protection: Review and Open Challenges", Applied Sciences, Vol. 11, Art. No. 1, 2021, https://dx.doi.org/10.3390/app11010001
  10. D. Megias, W. Mazurczyk, M. Kuribayashi, "Data Hiding and Its Applications: Digital Watermarking and Steganography", Applied Sciences, Vol. 11, Art. No. 10928, 2021, https://doi.org/10.3390/app112210928
  11. H. Kheddar, D. Megias, "High capacity speech steganography for the G723.1 coder based on quantised line spectral pairs interpolation and CNN auto-encoding", Applied Intelligence, Vol. 52, pp. 9441-9459, 2022, https://doi.org/10.1007/s10489-021-02938-7
  12. D. Megias, M. Kuribayashi, A. Rosales, K. Cabaj, W. Mazurczyk, "Architecture of a fake news detection system combining digital watermarking, signal processing, and machine learning", Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications (JoWUA), 2022, https://dx.doi.org/10.22667/JOWUA.2022.03.31.033
  13. D. Megias, D. Lerch-Hostalot, "Subsequent Embedding in Targeted Image Steganalysis: Theoretical Framework and Practical Applications", IEEE Transactions on Secure and Dependable Computing, Vol. 20, Issue 2, pp. 1403-1421, 2023, https://doi.org/10.1109/TDSC.2022.3154967
  14. 1. T. Yasui, T. Tanaka, A. Malik, M. Kuribayashi, "Coded DNN watermark: robustness against pruning models using constant weight code", Journal of Imaging, vol.8, no.6, 16pages, 2022, https://doi.org/10.3390/jimaging8060152
  15. A. Malik, M. Kuribayashi, S. M. Abdullahi, A. N. Khan, "Deepfake detection for human face images and videos: a survey", IEEE Access, vol.10, pp.18757-18775, 2022, https://doi.org/10.1109/access.2022.3151186
  16. M. T. Ahvanooey, X. Zhu, W. Mazurczyk, K. R. Choo, M. Conti, J. Zhang, "Misinformation Detection on Social Media: Challenges and The Road Ahead", IEEE IT Professional Magazine, 2022, https://doi.org/10.1109/MITP.2021.3120876

Presentations at International Academic Conferences:

  1. K. Cabaj, M. Kowalczyk, M. Gregorczyk, M. Choras, R. Kozik, W. Mazurczyk, "Strategies to Use Harvesters in Trustworthy Fake News Detection Systems," In Proc. of 16th International Conference on Computational Collective Intelligence (ICCCI 2024), 9-11 September 2024, Leipzig, Germany
  2. T. Koohpayeh Araghi, D. Megias, V. Garcia-Font, M. Kuribayashi, W. Mazurczyk, "Disinformation detection and source tracking using semi-fragile watermarking and blockchain," In Proc. of In Proceedings of the European Interdisciplinary Cybersecurity Conference (EICC 2024), Xanthi, Greece, 5-6 June 2024
  3. C. Tanaka, M. Kuribayashi, N. Funabiki, "Gait Recognition Scheme Focusing on Operating Characteristics at Feature Points Detected by OpenPose," Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2023), pp.600-606, 2023. https://doi.org/10.1109/APSIPAASC58517.2023.10317291
  4. R. Akai, M. Kuribayashi, N. Funabiki, "A Study on Eliminating Biased Node in Federated Learning," Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2023), pp.607-614, 2023. https://doi.org/10.1109/APSIPAASC58517.2023.10317147
  5. A. Ura, M. Kuribayashi, N. Funabiki, "Study on Face Landmark-Based Analysis for Synthetic Media Identification Generated by Adversarial Generative Networks," Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2023), pp.1673-1679, 2023. https://doi.org/10.1109/APSIPAASC58517.2023.10317492
  6. D. Lerch-Hostalot and D. Megias, "Real-world actor-based image steganalysis via classifier inconsistency detection," In Proceedings of the 18th International Conference on Availability, Reliability and Security (ARES 2023), Association for Computing Machinery, New York, NY, USA, Article 43, 19, 2023, DOI: 10.1145/3600160.3605042
  7. R. Kozik, W. Mazurczyk, K. Cabaj, A. Pawlicka, M. Pawlicki, M. Choras, "Combating Disinformation with Holistic Architecture, Neuro-symbolic AI and NLU Models", In Proc. of 10th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2023), Thessaloniki, Greece, 9-13 October 2023
  8. T. Koohpayeh Araghi, D. Megias, A. Rosales, "Toward the Selection of a Lightweight Authentication Technique for the Security of Smart Homes: Framework Architecture Based on a User Centric Design", In Computing Conference 2023, London, UK, 22-23 June 2023
  9. T. Koohpayeh Araghi, D. Megias, A. Rosales, "Evaluation and Analysis of Reversible Watermarking Techniques in WSN for Secure, Lightweight Design of IoT Applications: A Survey", In: Arai, K. (eds) Advances in Information and Communication. FICC 2023. Lecture Notes in Networks and Systems, vol 652. Springer, Cham. https://doi.org/10.1007/978-3-031-28073-3_47
  10. A. H. Zim, A. Ashraf, A. Iqbal, A. Malik, M. Kuribayashi, "A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp.1318-1323, 2022.
  11. A. Malik, A. Ashraf, H. Wu, M. Kuribayashi, "Reversible Data Hiding in Encrypted Text Using Paillier Cryptosystem", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp.1492-1496, 2022.
  12. K. Tsunomori, Y. Yamasaki, M. Kuribayashi, N. Funabiki, I. Echizen, "Detection and Correction of Adversarial Examples Based on JPEG-Compression-Derived Distortion", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp.1828-1833, 2022.
  13. M. S. Raval, M. Roy, M. Kuribayashi, "Survey on Vision Based Fake News Detection and Its Impact Analysis", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp. 1834-1838, 2022.
  14. P. Raval, H. Khakhi, M. Kuribayashi, M. S. Raval, "Defense Against Adversarial Examples Using Beneficial Noise", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp. 1839-1845, 2022.
  15. H. Takiwaki, M. Kuribayashi, N. Funabiki, M. S. Raval, "Privacy Protection Against Automated Tracking System Using Adversarial Patch", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp.1846-1851, 2022.
  16. M. Kuribayashi, K. Kamakari, N. Funabiki, "Classification of Screenshot Image Captured in Online Meeting System", International IFIP Cross Domain Conference for Machine Learning & Knowledge Extraction (CD-MAKE2022), LNCS 13480, pp.244-255, Springer-Verlag, 2022, https://doi.org/10.1007/978-3-031-14463-9_16.
  17. R. Parmar, M. Kuribayashi, H. Takiwaki, M. S Raval, "On Fooling Facial Recognition Systems using Adversarial Patches", The 2022 International Joint Conference on Neural Networks (IJCNN 2022), pp.1-8, 2022, https://doi.org/10.1109/IJCNN55064.2022.9892071.
  18. M. Kowalczyk, A. Malanowska, W. Mazurczyk, K. Cabaj, "Web Page Harvesting for Automatized Large-scale Digital Images Anomaly Detection", In Proc. of Criminal Use of Information Hiding (CUING) Workshop, In Proceedings of the 17th International Conference on Availability, Reliability and Security (ARES '22). ACM, Article 47, 1-9. https://doi.org/10.1145/3538969.3544471.
  19. J. Hospital, D. Megias, W. Mazurczyk, "Retransmission steganography in real-world scenarios: a practical study", In Proc. of European Interdisciplinary Cybersecurity Conference (EICC), Virtual, November 2021, pp. 60-65, DOI: 10.1145/3487405.3487659.
  20. A. Qureshi, D. Megias, M. Kuribayashi, "Detecting deepfake videos using digital watermarking", Asia-Pacific Signal and Information Processing Association Anual Sumit and Conf. (APSIPA ASC 2021), pp.1786-1793, 2021, https://ieeexplore.ieee.org/document/9689555.
  21. D. Takeshita, M. Kuribayashi, N. Funabiki, "A study of feature extraction suitable for double JPEG compression analysis based on statistical bias observation of DCT coefficients", Asia-Pacific Signal and Information Processing Association Anual Sumit and Conf. (APSIPA ASC 2021), pp.1808-1814, 2021.
  22. Y. Yamasaki, M. Kuribayashi, N. Funabiki, H. H. Nguyen, I. Echizen, "A study of feature extraction based on denoising auto encoder for classification of adversarial examples", Asia-Pacific Signal and Information Processing Association Anual Sumit and Conf. (APSIPA ASC 2021), pp.1815-1820, 2021.
  23. K. Nakai, M. Kuribayashi, N. Funabiki, "A study of privacy protection of photos taken by wide-angle surveillance camera", Asia-Pacific Signal and Information Processing Association Anual Sumit and Conf. (APSIPA ASC 2021), pp.1865-1871, 2021.
  24. D. Megias, M. Kuribayashi, A. Rosales, W. Mazurczyk, "DISSIMILAR: Towards fake news detection using information hiding, signal processing and machine learning", in The 16th Int. Conf. Availability, Reliability and Security (ARES2021), Art. No. 66, pp. 1-9, 2021, https://doi.org/10.1145/3465481.3470088
  25. M. Kuribayashi, T. Tanaka, S. Suzuki, T. Yasui, and N. Funabiki, "White-box watermarking scheme for fully-connected layers in fine-tuning model", 9th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec'21), pp.165-170, 2021.

Presentations at Domestic Academic Conferences:

  10. V. Garcia-Font, T. Koohpayeh Araghi, D. Megias, H. Rifa, J. Salas, and J. Serra-Ruiz, "Arquitectura para la Deteccion de Noticias Falsas Basada en Watermarking y Machine Learning", In: Actas de la XVII Reunion Espanola sobre Criptologia y Seguridad de la Informacion (RECSI 2022), Santander, Spain, 19-21 October 2022, pp. 205-211. DOI: https://doi.org/10.22429/Euc2022.028. ISBN: 978-84-19024-14-5.
  14. 角森健太, 山﨑裕真, 栗林", 舩曵信", 越前功, "JPEG圧縮"来の歪み信号に 対する応"特性に基づくAdversarial Examples検知手法," 2022年暗号と情報セ キュリティシンポジウム (SCIS2022), 2022.
  15. 鎌苅康大, 栗林", 舩曵信", "オンライン会議システム上の"面キャプチャに よる情報漏洩の対策の一検討," 2022年暗号と情報セキュリティシンポジウム (SCIS2022), 2022.
  16. "中"朗, 安井"", 栗林", 舩曵信", "埋め込みロス関数なしのDNN電子透か しの収束に関する考察," 信学技報, EMM 11月, 2021.
  17. 山﨑裕真, 栗林", 舩曵信", グエン フイ ホン, 越前功, "複数のAuto Encoderに対する応"特性を"いた敵対的事例の検出法," 信学技報, EMM 5月, 2021.
  18. 竹下大地, 栗林", 舩曵信", "DCT係数の統計的な偏り観測における二重JPEG圧 縮履歴解析に適した特徴成分選出に関する考察," 信学技報, EMM 5月, 2021.

Invited Talks:

  3. W. Mazurczyk, "Stare chwyty, nowe metody - jak wykorzystac sztuczna inteligencje", Festiwal Nauki, Warsaw, Poland, 15 September 2023
  4. D. Megias, "Detection of fake news on social media platforms (DISSIMILAR)", I International Workshop on Disinformation Research, Malaga (Spain), 4-5 July 2023
  5. M. Kuribayashi, "Classification of Fake Content Created by Generative AI," Invited Speech, International Conference on Computer and Communications Management (ICCCM 2023), August 2023.
  6. M. Kuribayashi, "Multimedia Forensics for Fake Content Classification", Keynote Talk International Conference on Emerging Computational Intelligence (ICECI 2023), February 2023.
  7. M. S. Raval, M. Roy, M. Kuribayashi, "Fake News Detection and its impact analysis," Tutorial, APSIPA ASC 2022, November 2022.
  9. W. Mazurczyk, "Sposoby detekcji fake news w tresciach multimedialnych w projekcie DISSIMILAR - podejscie interdyscyplinarne", Seminarium Wybrane zastosowania inteligencji obliczeniowej, Komisja Informatyki i Automatyki PAN, 25 November, 2022
  10. 兵庫県立豊岡高等学校 【STEAM講"会】"ディープフェイクを見破れ!", 栗林", 2021年11月
  11. 新時代の日本を考える兵庫フォーラム, "ディープフェイクを見破れ～サイバー 空"における情報戦の最前線～," 栗林", 2021年5月.

Organizing Workshops, Seminars, Symposium, Special issues, etc.:

  1. ARES 2024: co-organization of International Workshop on Criminal Use of Information Hiding (CUING 2024), 2024.
  2. APSIPA ASC 2023, Tutorial, "Spoofing Face Recognition Systems with Adversarial Examples: Challenges and Countermeasures", 2023.
  3. ARES 2023: co-organization of International Workshop on Criminal Use of Information Hiding (CUING 2023), 2023.
  4. APSIPA ASC 2022: organization of special session on "Emerging Trends in Privacy, Multimedia Security and Forensics: Deep Learning and AI Approaches", 2022
  5. APSIPA ASC 2022: organization of special session on "Adversarial Attack and Defense", 2022.
  6. APSIPA ASC 2022: Tutorial "Fake News Detection and its Impact Analysis", 2022.
  7. ARES 2022: co-organization of International Workshop on Criminal Use of Information Hiding (CUING 2022), 2022.
  8. Applied Sciences, organization of special issue on Data Hiding and Its Applications: Digital Watermarking and Steganography (Volume II), MDPI, ISSN: 2076-3417, 2022.
  9. Applied Sciences, organization of special issue on Data Hiding and Its Applications: Digital Watermarking and Steganography (Volume I), MDPI, ISSN: 2076-3417, 2021.
  10. ICIP 2021: organization of special session on "Artificial Intelligence for Multimedia Security and Deepfake", 2021.
  11. APSIPA ASC 2021: organization of special session on "Deep Generative Models for Media Clones and Its Detection", 2021.

DISSIMILAR in media

Press releases

  1. , 2022 (in Japanese)
  2. (in Japanese)
  3. IEEE Consumer Technology, "Featured People: Interview with Prof. Minoru Kuribayashi" (in English), News on Consumer Technology (NCT), September 2022 Issue
  4. Hechos De Hoy, "Como la tecnologia puede detectar fake news en video" (in Spanish), June 2022
  5. MetaData, "Investigadors de la UOC utilitzen intelligencia artificial per detectar 'deepfakes'" (in Catalan), June 2022
  6. Alpha Galileo, "Como la tecnologia puede detectar fake news en video" (in Spanish), June 2022
  7. La Vanguardia, "UOC lidera proyecto para distinguir contenidos multimedia originales y falsos" (in Spanish), June 2022
  8. BSc.org, "How technology can detect fake news in videos" (in English), July 2022
  9. Eurekalert!, "How technology can detect fake news in videos" (in English), July 2022
  10. Comunicacio21, "Tecnologia para desenmascarar los deepfakes" (in Catalan), July 2022
  11. Silicon, "Tecnologia para desenmascarar los deepfakes" (in Spanish), July 2022
  12. Digital Journal, "New technology challenges fake news and disinformation" (in English), July 2022
  13. TecnonewsCat, "Com la tecnologia pot detectar fake news en video" (in Catalan), July 2022
  14. UoC website, "How technology can detect fake news in videos" (in English), June 2022
  15. WirtualneMedia, "Algorytmy naukowców Politechniki Warszawskiej pomogą w walce z dezinformacją" (in Polish), April 2022
  16. Polskie Radio Program Czwarty, "Politechnika Warszawska zwalczy dezinformacje" (in Polish), April 2022
  17. Polskie Radio Program Trzeci, "Algorytmy skuteczna bronią do walki z dezinformacją?" (in Polish), April 2022
  18. Stowarzyszenie Dziennikarzy Polskich, "Naukowcy z Politechniki Warszawskiej tworzą algorytmy, które pomogą walczyc z fake newsami" (in Polish), April 2022
  19. DignityNews.pl, "Na Politechnice Warszawskiej nauczą maszyny walki z dezinformacją" (in Polish), April 2022
  20. Nauka w Polsce, "Algorytmy naukowców PW pomogą w walce z dezinformacją" (in Polish), April 2022
  21. Warsaw University of Technology website, "Sztuczna inteligencja na froncie walki z dezinformacją" (in Polish), April 2022
  22. NASK Thinkstat, "AI i cyfrowe znaki wodne " czy obronią nas przed falą fake newsów?" (in Polish), November 2021
  23. Android.com.pl, "Cyfrowe znaki wodne mogą pomóc w walce z fake newsami" (in Polish), November 2021
  24. Science in Poland, "Oryginał czy przeróbka? Cyfrowe znaki wodne mają wspomóc walkę z fake newsami" (in Polish), October 2021
  25. Chip, "Naukowcy z Polski, Japonii i Hiszpanii łączą siły w walce z fake newsami" (in Polish), October 2021
  26. WirtualneMedia, "Cyfrowe znaki wodne mają wspomóc walkę z fake newsami" (in Polish), October 2021
  27. Warsaw University of Technology website, "To nie fejk! To prawdziwy news!" (in Polish), October 2021