The Media Asset Annotation Management (MAAM) platform is a web-based tool designed to help media professionals, journalists, and fact-checkers verify the authenticity of digital media. MAAM offers a unique combination of media management and AI-powered disinformation detection features.

Users can easily upload, organize, and search through collections of images and videos using advanced annotation and filtering tools. At the same time, MAAM leverages cutting-edge AI models to detect signs of manipulation — such as deepfakes, synthetic media, and image tampering — and provides explainable insights to support informed verification decisions.

Demo More

The DeepFake detector is a prototype demonstrator of our deepfake detection algorithm. It processes an image or video and returns the probability that it contains deepfake-manipulated faces.

The demo is password-protected. In case of interest, requests for trial should be made by email at verifymedia@iti.gr stating the purpose of use.

Demo

The Media Verification Assistant features a multitude of image tampering detection algorithms plus metadata analysis, GPS Geolocation, EXIF Thumbnail extraction and integration with Google reverse image search.

Demo GitHub

The location estimation is a prototype demonstrator, which, given an image (its URL), provides an estimate of the depicted location (if any) based on visual analysis of its content.

The demo is password-protected. In case of interest, requests for trial should be made by email at verifymedia@iti.gr stating the purpose of use.

Demo

This is a prototype system that supports reverse video search on a large collection of web videos. It consists of:

• Α search operation where the user provides the URL of an input video in the “search” box and the system retrieves from its “index” a set of videos that are highly similar in terms of visual appearance. Similar videos often correspond to near-duplicate or partial duplicate versions of the input video, while there are also cases where related videos from the same event are retrieved.
• The video “index” which is the FIVR-200K dataset, a collection of more than 200 thousands of videos from YouTube that were posted between the beginning of 2013 and end of 2017 and are related to queries related to natural disasters, accidents and war events. In addition to this fixed video collection, users can extend the index by issuing new queries to YouTube in the “Add” page. Note that adding videos to index is a relatively time-consuming process, because several queries need to be issued to YouTube and then the videos need to be analysed.

The demo is password-protected. In case of interest, requests for trial should be made by email at verifymedia@iti.gr stating the purpose of use.

Demo

This prototype web application offers a network-based visualization of online social media conversations with the goal of helping users gain insights about how information is spreading in the network and how the groups frequently communicating with each other form communities. In the current setup, the nodes of the network correspond to Twitter accounts and the edges represent Twitter interactions (mention, reply, retweet) between the accounts.

Unfortunately, the MeVer NetworkX tool is now outdated due to recent changes in platform APIs. The Twitter API, which was essential for obtaining input data, is no longer accessible. Similarly, Crowdtangle, the source for Facebook data, is also unavailable. These limitations have forced the suspension of the tool until the platforms’ APIs become accessible again or until there is an alternative method for obtaining input data.

A more detailed technical presentation and several use cases are included in the associated journal article.

Demo

This is a demo platform aimed to facilitate the verification of UGC video content posted on YouTube, Twitter and Facebook. In contrast to other approaches, which attempt to analyze the videos themselves for traces of forgery, this platform analyzes the video context: The characteristics of the poster, any relevant user comments, the local weather reports at the time of the event, and other contextual pieces of information are aggregated and presented to the user for analysis.

Unfortunately, the CAA tool is now outdated due to recent changes in platform APIs. The Twitter/X API, which was essential for obtaining the required information, is no longer accessible. This limitation has forced the suspension of the tool until the platform’s API becomes accessible again or until there is an alternative method for obtaining the data.

A more detailed technical presentation and several use cases are included in the associated conference paper.

Demo

Get help in analyzing the veracity of a tweet. Given a tweet, a user can explore the verification result, including the extracted feature values and their distribution on the Verification Corpus.

Unfortunately, the Tweet Verification Assistant is now outdated due to recent changes in platform APIs. The Twitter/X API, which was essential for obtaining the tweet, is no longer accessible. This limitation has forced the suspension of the tool until the platform’s API becomes accessible again or until there is an alternative method for obtaining the data.

A more detailed technical presentation and several use cases are included in the associated journal article.

Demo