AI RESEARCH
From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering
arXiv CS.AI
•
ArXi:2603.20193v1 Announce Type: cross Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially modified, while subtle yet consequential edits outside the mask are treated as natural. We reformulate VLM image tampering from coarse region labels to a pixel-grounded, meaning and language-aware task. First, we