Scientists at the Warsaw University of Technology are developing algorithms using artificial intelligence that will act as a dam against the flood of fake news. The work is carried out under the international DISSIMILAR project together with researchers from Okayama University (Japan) and Fundació per a la Universitat Oberta de Catalunya (Spain).

It is estimated that over 4.2 billion people use online communication platforms today. Unfortunately, social media does not have built-in tools to verify the truthfulness of the provided information, and public opinion is often shaped by fake news.

Disinformation is a special type of threat because it directly influences public opinion, shaping a specific attitude around sensitive events and issues, such as the price of energy, the annexation of Crimea, the war in Ukraine, etc.

Data from the state-owned research institute NASK, which analyzed 1,500 profiles in social media for a month under the # EnableVerification campaign, show that as much as 30% of the audited accounts were aimed at misleading recipients. The aim of the DISSIMILAR project is to build an effective tool to automatically separate false information and block its spread.

“We are in the process of developing a virtual platform that will be used to test the mechanisms of watermarking, machine learning and computer forensics – i.e. the methods that we will use in the fight against fake news – says Prof. Wojciech Mazurczyk, a leader of the Polish team in the DISSIMILAR project.

The results of the project can also be used as a tool to protect the authors of the published content. Digital marking techniques, i.e. so-called Watermarks in protected content that are invisible and inaudible, and their removals are immediately visible, will provide creators with an effective copyright protection tool.

Arkadiusz Słomczyński