Determining Intent of Changes to Ascertain Fake Crowdsourced Image Services
This addresses the issue of trust in social media content for users and platforms, but appears incremental as it builds on existing metadata-based approaches.
The paper tackles the problem of detecting fake crowdsourced images on social media by proposing a framework that uses image metadata and models images as services, focusing on the intention of changes to assess fakeness, achieving high accuracy on a large real dataset.
We propose a novel framework for crowdsourced images to determine the likelihood of an image being fake. We use a service-oriented approach to model and represent crowdsourced images uploaded on social media, as image services. Trust may, in some circumstances, be determined by using only the non-functional attributes of an image service, i.e., image metadata. We define intention of changes as a key parameter to ascertain fake image services. A novel framework is proposed to estimate the intention of underlying changes considering change in semantics of an image. Our experiments show high accuracy using a large real dataset.