Detecting Adversarial Examples Using Cross-Modal Semantic Embeddings From Images and Text

Detecting Adversarial Examples Using Cross-Modal Semantic Embeddings From Images and Text

Deep learning models are highly susceptible to adversarial attacks, where subtle perturbations in the input images lead to misclassifications. Adversarial examples typically distort specific features that are critical for accurate image classification. Therefore, distorting the visual semantic chara...

Full description

Bibliographic Details
Main Authors: Sohee Park, Gwonsang Ryu, Daeseon Choi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Multimodal learning
cross-modal embedding
adversarial attack
adversarial example detection
image classification
Online Access:https://ieeexplore.ieee.org/document/10891646/

Internet

https://ieeexplore.ieee.org/document/10891646/

Similar Items