Napguard: Towards detecting naturalistic adversarial patches

S Wu, J Wang, J Zhao, Y Wang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Recently the emergence of naturalistic adversarial patch (NAP) which possesses a
deceptive appearance and various representations underscores the necessity of develo** …

Isolation and induction: Training robust deep neural networks against model stealing attacks

J Guo, X Zheng, A Liu, S Liang, Y **ao, Y Wu… - Proceedings of the 31st …, 2023 - dl.acm.org
Despite the broad application of Machine Learning models as a Service (MLaaS), they are
vulnerable to model stealing attacks. These attacks can replicate the model functionality by …

Multi-modal Prompts with Feature Decoupling for Open-Vocabulary Object Detection

D Wang, X Zhao - International Joint Conference on Artificial Intelligence, 2024 - Springer
Open-vocabulary object detection aims to acquire the ability to recognize novel categories
through text description using data of limited categories for training. The Prompt serves as a …

The impacts of artificial intelligence techniques in augmentation of cyber security

R ** - 2024 IEEE 6th International Conference on Civil …, 2024 - ieeexplore.ieee.org
In order to optimise deep learning models for few-shot website fingerprinting (WF) attacks,
this study offers a fresh way to data augmentation technique. For each website, only a few …

Multi-modal Prompts with Feature Decoupling for Open-Vocabulary Object

D Wang, X Zhao - Generalizing from Limited Resources in the …, 2024 - books.google.com
Open-vocabulary object detection aims to acquire the abil-ity to recognize novel categories
through text description using data of limited categories for training. The Prompt serves as a …