ForClu automatically arranges contents seized from a suspect’s device into meaningful clusters. It analyses data, (e.g. images), using Unsupervised Machine Learning, generating mathematical “concepts” of the pictures. Those concepts are used in arranging them into clusters, which solely depend on the input data. For example all pictures of cars, which are then further divided into sub-categories (sedans, vans, SUVs,…). ForClu can be used as a standalone toolkit, but integration into LEAP or into existing forensic toolkits is also evaluated.
STRENGTHS
ForClu can work with 100.000+ files at the same time.
ForClu allows creating filters for very specific contents, such as details of clothing of a person or a specific
build and color of a car you are looking for.
The filters are highly abstracted, so no actual pictures can be retrieved from them.
Upcoming features include the possibility to share filters, to help deal with privacy issues within a government
agency or even between different agencies.