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.
Attentional feature erase: Towards task-wise transferable ad- versarial attack on cloud vision apis
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.