JMOF is a new optimization framework for physical adversarial attacks that improves cross-model transferability and enables simultaneous attacks on multiple vision tasks such as object detection and semantic segmentation.
Generate transferable adversarial physical camouflages via triplet attention suppression,
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
-
Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework
JMOF is a new optimization framework for physical adversarial attacks that improves cross-model transferability and enables simultaneous attacks on multiple vision tasks such as object detection and semantic segmentation.