JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.
In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
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
-
JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.