Verification Plugin

This browser extension is a toolbox providing journalists, fact-checkers, human rights defenders, media literacy scholars, researchers and the general public with a variety of tools aimed to empower and help them to verify cross-modal information and to debunk disinformation.

Truly Media Workbench

The workbench enables verification professionals to work in a distributed fashion, assisted by the automated algorithms for cross-modal content verification and social network analysis.

Deepfake Detector

The Deepfake Detector tool processes media items (images or videos) and returns the probability that this media contains deepfake manipulated faces.

Visual Location Estimation

The Visual Location Estimation tool aims to infer locations using the visual content of an image.

AuSIL - Audio-based Near-Duplicate Video Retrieval

The AuSIL tool aims to find near duplicate videos taking into account the audio part of the videos.

Super Resolution

Super-resolution increases the resolution of an image beyond the original capabilities of the sensor, which can allow “zooming in” or “deblurring” to analyze an image or video frame and provide the user with information that could otherwise be impossible to read.

Network Visualization

A prototype web application that offers a network-based visualization of online social media conversations aiming to help users gain insights about how information spreads in the network and how the groups frequently communicating with each other form communities.

Image Verification Assistant

The tool consists of a set of image forensics algorithms that try to find traces of forgeries in the query images.

Context Aggregation and Analysis

The tool facilitates the verification of user-generated images that derives from Facebook and Twitter and videos from Youtube, Facebook and Twitter.

Near Duplicate Detection

A tool providing reverse video search on a large collection of videos.

OCR for Memes, Adverts and Other Images

A tool specifically tuned to extracting the text from memes, adverts, and other images.

Domain Credibility Service

This service tags URLs or domain names within a given text, flagging those which have previously been judged by journalists or fact-checking organisations as having low credibility.

Stance Classification

Given an original textual statement and one or more replies to that statement (e.g. a tweet and a reply tweet) this service determines the stance of each reply, i.e. whether it supports/agrees with, denies/disagrees with, queries, or comments on the original statement.

COVID-19 Misinformation Classifier

Categorises COVID-19 misinformation into one of 10 categories, including government actions, impact on community, medical advice, conspiracy theories, vaccine, etc.

Rumour Veracity Service

Classifies social media posts based on whether the claims made within it are likely true, false or need further verification.