A single adversarial image can make a unified vision-language model misclassify the same object across captioning, detection, region classification, and localization, and the new CrossVLAD benchmark and CRAFT attack measure and achieve this.
On the robustness of large multimodal mod- els against image adversarial attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models
A single adversarial image can make a unified vision-language model misclassify the same object across captioning, detection, region classification, and localization, and the new CrossVLAD benchmark and CRAFT attack measure and achieve this.