EntropyScan detects backdoored LVLMs by quantifying structural anomalies in visual attention distributions on benign samples via Tsallis entropy and reference-anchored Z-score normalization.
In: Proceed- ings of the 31st ACM International Conference on Multimedia (ACM MM)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
EntropyScan detects backdoored LVLMs by quantifying structural anomalies in visual attention distributions on benign samples via Tsallis entropy and reference-anchored Z-score normalization.