Independently optimized decoy patches redirect ViT attention-based defenses away from true adversarial regions while largely preserving attack success.
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this information can be used to perform segmentation or single-view depth estimation even though the networks were only trained for image recognition. We show that a similar phenomenon occurs when explicitly training transformers for semantic segmentation in a supervised manner for a set of categories: Once trained, they provide valuable information even about categories absent from the training set. This information can be used to segment objects from these never-seen-before classes in domains as varied as road obstacles, aircraft parked at a terminal, lunar rocks, and maritime hazards.
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
Independently optimized decoy patches redirect ViT attention-based defenses away from true adversarial regions while largely preserving attack success.