MA‐CAT: Misclassification‐Aware Contrastive Adversarial Training
Vulnerability to adversarial examples poses a significant challenge to the secure application of deep neural networks. Adversarial training and its variants have shown great potential in addressing this problem. However, such approaches, which directly optimize the decision boundary, often result in overly complex adversarial decision boundaries that are detrimental to generalization. To deal with this issue, a novel plug‐and‐play method known as Misclassification‐Aware Contrastive Adversarial Training (MA‐CAT) from the perspective of data distribution optimization is proposed. MA‐CAT leverages supervised decoupled contrastive learning to cluster nature examples within the same class in the logit space, indirectly increasing the margins of examples. Moreover, by taking into account the varying difficulty levels of adversarial training for different examples, MA‐CAT adaptively customizes the strength of adversarial training for each example using an instance‐wise misclassification‐aware adaptive temperature coefficient. Extensive experiments on the CIFAR‐10, CIFAR‐100, and SVHN datasets demonstrate that MA‐CAT can be easily integrated into existing models and significantly improves robustness with minimal computational cost.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
MA‐CAT: Misclassification‐Aware Contrastive Adversarial Training ; day:05 ; month:02 ; year:2024 ; extent:10
Advanced intelligent systems ; (05.02.2024) (gesamt 10)
- Creator
-
Zhi, Hongxin
Yu, Hongtao
Li, Shaomei
Huang, Ruiyang
- DOI
-
10.1002/aisy.202300658
- URN
-
urn:nbn:de:101:1-2024020514190631933836
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
15.08.2025, 7:24 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Zhi, Hongxin
- Yu, Hongtao
- Li, Shaomei
- Huang, Ruiyang
Other Objects (12)
A3T: accuracy aware adversarial training
Intent with knowledge-aware multiview contrastive learning for recommendation
Defect-aware Super-resolution Thermography by Adversarial Learning
Topology-aware universal adversarial attack on 3D object tracking
Semantic-aware deidentification generative adversarial networks for identity anonymization
Adversarial Distillation Adaptation Model with Sentiment Contrastive Learning for Zero-Shot Stance Detection
Multi-channels Prototype Contrastive Learning with Condition Adversarial Attacks for Few-shot Event Detection
Toward metacognition: subject-aware contrastive deep fusion representation learning for EEG analysis
Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks
MR-contrast-aware image-to-image translations with generative adversarial networks
Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks
MR-contrast-aware image-to-image translations with generative adversarial networks
A3T: accuracy aware adversarial training
Intent with knowledge-aware multiview contrastive learning for recommendation
Defect-aware Super-resolution Thermography by Adversarial Learning
Topology-aware universal adversarial attack on 3D object tracking
Semantic-aware deidentification generative adversarial networks for identity anonymization
Adversarial Distillation Adaptation Model with Sentiment Contrastive Learning for Zero-Shot Stance Detection
Multi-channels Prototype Contrastive Learning with Condition Adversarial Attacks for Few-shot Event Detection
Toward metacognition: subject-aware contrastive deep fusion representation learning for EEG analysis
Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks
MR-contrast-aware image-to-image translations with generative adversarial networks
Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks
MR-contrast-aware image-to-image translations with generative adversarial networks
A3T: accuracy aware adversarial training
Intent with knowledge-aware multiview contrastive learning for recommendation
Defect-aware Super-resolution Thermography by Adversarial Learning
Topology-aware universal adversarial attack on 3D object tracking
Semantic-aware deidentification generative adversarial networks for identity anonymization
Adversarial Distillation Adaptation Model with Sentiment Contrastive Learning for Zero-Shot Stance Detection
Multi-channels Prototype Contrastive Learning with Condition Adversarial Attacks for Few-shot Event Detection
Toward metacognition: subject-aware contrastive deep fusion representation learning for EEG analysis
Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks
MR-contrast-aware image-to-image translations with generative adversarial networks
Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks