Publication:

How AI-Based Regeneration Reshapes Multimedia Forensics

Date

 
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid0000-0002-0660-3190
cris.virtualsource.department817f2cb4-7e19-4453-9161-77eae0680f92
cris.virtualsource.orcid817f2cb4-7e19-4453-9161-77eae0680f92
dc.contributor.authorMareen, Hannes
dc.date.accessioned2026-11-16T13:49:42Z
dc.date.available2026-11-16T13:49:42Z
dc.date.createdwos2026
dc.date.issued2026
dc.description.abstractDiffusion models are widely known for generating new images from text, but their capabilities extend much further, into restoration, enhancement, editing, and compression. These AI tools unlock impressive creative and technical possibilities, but also blur the line between real and synthetic content, posing new challenges for multimedia forensics. First, AI-based compression may appear content-preserving, yet it can subtly alter image semantics [2]. This poses serious risks, for instance, when analyzing sensitive material such as surveillance footage. Moreover, such processing can introduce artifacts resembling those of generative models, meaning authentic media might be incorrectly flagged as synthetic [3]. Even more disruptive, diffusion-based regeneration can erase forensic traces used for watermarking [4], deepfake detection, or image forgery localization [1]. This can occur intentionally in targeted attacks or unintentionally through image processing such as super-resolution [5]. Finally, current image forgery localization methods fail to localize edits performed by new AI-based inpainting methods because they fully regenerate the edited images [5, 6]. As AI-based regeneration becomes embedded in everyday media workflows, multimedia forensics must evolve to safeguard trust in visual evidence in the era of generative AI. Future research could explore automated detection of miscompressions, detection of a media’s processing history, and forensic methods robust to laundering.
dc.description.wosFundingTextThis work was funded in part by the Flemish government, by IDLab (Ghent University - imec), by Flanders Innovation & Entrepreneurship (VLAIO), by Research Foundation - Flanders (FWO), and by the European Union.
dc.identifier.doi10.1145/3810988.3812664
dc.identifier.isbn979-8-4007-2700-9
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/60810
dc.language.isoeng
dc.provenance.editstepusergreet.vanhoof@imec.be
dc.publisherASSOC COMPUTING MACHINERY
dc.source.beginpage1
dc.source.conference5th ACM International Workshop on Multimedia AI against Disinformation - MAD
dc.source.conferencedate2026
dc.source.conferencelocationAmsterdam
dc.source.endpage1
dc.source.journalPROCEEDINGS OF THE 5TH ACM INTERNATIONAL WORKSHOP ON MULTIMEDIA AI AGAINST DISINFORMATION, MAD 2026
dc.source.numberofpages1
dc.title

How AI-Based Regeneration Reshapes Multimedia Forensics

dc.typeProceedings paper
dspace.entity.typePublication
imec.internal.crawledAt2026-06-15
imec.internal.sourcecrawler
imec.internal.wosCreatedAt2026-11-14
Files

Original bundle

Name:
3810988.3812664.pdf
Size:
966.41 KB
Format:
Adobe Portable Document Format
Description:
Published
Publication available in collections: