Tracking and Detecting Fake News and Deepfakes in Arabic Social Networks

The 4th Generation War (4GW) is known as an information war involving non-military populations. It is conducted by national or transnational groups following ideologies based on cultural beliefs, religion, economic or political interests, aiming to sow chaos in a targeted region globally. In 1989, authors discussing the 4th generation war, some of whom were military experts, explained that it would be widespread and challenging to define in the decades to come.

With the emergence of social networks, the previously vague battlefield found a platform for 4GW. One of its penetration points is the extensive use of social networks to manipulate opinions, aiming to shape the targeted region’s perspective to accept a certain state of affairs and render it socially and politically acceptable.

Much like the 4th generation war, cognitive warfare aims to blur comprehension mechanisms regarding politics, economy, religion, etc. Its consequence is destabilizing and weakening the adversary. This cognitive war targets what is assumed to be the enemy’s brain, altering reality by flooding the adversary’s population with misleading information, rumors, or manipulated videos.

Furthermore, the proliferation of social bots today enables automated dissemination of disinformation on social networks. According to some sources, for the 2016 US elections, 19% of the total tweet volume was generated by these automated robots.

Within TRADEF, we focus on various avenues of disinformation: fake news, deepfakes, and potentially harmful information. The aim is to rapidly detect the birth of fake news—whether textual, audio, or video—in social networks and trace its propagation. This involves monitoring and attributing confidence scores to the potential rumors across networks, in the reference language and other languages. The suspicious information’s evolution over time will alter its score based on encountered data. The information under scrutiny will be matched with audio or video data that can confirm or refute its credibility. Videos serving as sources to expose fake news might themselves be deepfakes. Thus, we must be vigilant in scrutinizing these videos by developing robust deepfake detection methods. Finally, an explicability dimension is introduced into this project.

Given the participating teams’ experience in deep learning and automatic processing of standard Arabic language and its dialects, our goal is to track and identify fakes and potentially harmful information in Arabic social networks. This also leads to other scientific challenges, including code-switching handling, variability in Arabic dialects, identifying named entities in speech continuum, developing neural methods for low-resource languages, and explaining obtained results.

Partnership List:

  • Université de Lorraine (LORIA)
  • LIA Laboratoire d’Informatique d’Avignon

Project Coordinator: LORIA

Scientific Lead for LIA: Yannick ESTEVE

Start Date: 01/01/2023 End Date: 31/12/2025