With the rapid proliferation of inexpensive acquisition and storage devices multimedia objects can be easily created, stored, transmitted, modified and tampered with by anyone. During its lifetime, a digital object might go through several processing stages, including multiple analog-to-digital (A/D) and digital-to-analog (D/A) conversions, coding and decoding, transmission, editing (either aimed at enhancing the quality, creating new contents mixing pre-existing materials, or tampering with the content). The REWIND (REVerse engineering of audio- VIsual coNtent Data) project is aimed at synergistically combining principles of signal processing, machine learning and information theory to answer relevant questions on the past history of such objects. The REWIND proposal starts from the observation that each of these processing steps necessarily leaves a characteristic footprint, which can be potentially detected to trace back the past history of the available multimedia object in a blind fashion, i.e. without having access to the original content. Note that, in many cases, these processing steps introduce undesired and irreversible distortions ("misprints") in the original multimedia object, e.g. due to insufficient sampling rate in the acquisition phase, coding artifacts in lossy compression, or imperfect error concealment strategies. Considerable efforts in multimedia processing research have been directed therefore towards a more comprehensive understanding of how to prevent these artifacts through, for instance, error-resilience mechanisms or techniques to avoid undesired or unauthorized modifications of the content streams.REWIND intends to develop innovative tools and approaches to reverse this perspective completely: footprints are considered as an asset, i.e. a source of additional information about the multimedia object history, which can be leveraged to reconstruct the processing chain applied to the audio-video digital object.