Results 31 to 40 of about 852,288 (193)
Internal Wasserstein Distance for Adversarial Attack and Defense [PDF]
, 2023 Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks that would trigger misclassification of DNNs but may be imperceptible to human perception.
Wang, Qicheng +5 more
core +1 more source
Ensemble Adversarial Example Defense Based on Generative Adversarial Network
工程科学与技术, 2022 Given the bottlenecks of existing adversarial example defense schemes, such as insufficient defense capability and high time consumption, an ensemble adversarial example defense scheme based on the generative adversarial network was proposed in this ...
Tianjie CAO +5 more
doaj
Defending Against Adversarial Fingerprint Attacks Based on Deep Image Prior
IEEE Access, 2023 Recently, deep learning-based biometric authentication systems, especially fingerprint authentication, have been used widely in real-world. However, these systems are vulnerable to adversarial attacks which prevent deep learning models from ...
Hwajung Yoo +4 more
doaj +1 more source
The Defense of Adversarial Example with Conditional Generative Adversarial Networks [PDF]
Security and Communication Networks, 2020 Deep neural network approaches have made remarkable progress in many machine learning tasks. However, the latest research indicates that they are vulnerable to adversarial perturbations. An adversary can easily mislead the network models by adding well-designed perturbations to the input. The cause of the adversarial examples is unclear.
Fangchao Yu +3 more
openaire +2 more sources
Defense Against Universal Adversarial Perturbations [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to `any' image can fool a state-of-the-art network classifier to change its prediction about the image label. These `Universal Adversarial Perturbations' pose a serious threat to the success of Deep Learning in practice.
Naveed Akhtar, Jian Liu 0014, Ajmal Mian
openaire +3 more sources
Adversarial attack and defense on graph neural networks: a survey
网络与信息安全学报, 2021 For the numerous existing adversarial attack and defense methods on GNN, the main adversarial attack and defense algorithms of GNN were reviewed comprehensively, as well as robustness analysis techniques.Besides, the commonly used benchmark datasets and ...
Jinyin CHEN +4 more
doaj +3 more sources
GUARD: Graph Universal Adversarial Defense [PDF]
, 2023 Graph convolutional networks (GCNs) have been shown to be vulnerable to small adversarial perturbations, which becomes a severe threat and largely limits their applications in security-critical scenarios.
Wu, Ruofan +7 more
core
Scaling provable adversarial defenses
CoRR, 2018 Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this paper, in an effort to scale these approaches to substantially larger models, we extend previous work in three ...
Eric Wong 0001 +3 more
openaire +4 more sources
Textual Adversarial Training Method Based on Distributed Perturbation [PDF]
Jisuanji gongcheng, 2023 Text adversarial defense aims to enhance the resilience of neural network models against different adversarial attacks. The current text confrontation defense methods are usually only effective against certain specific confrontation attacks and have ...
Zhidong SHEN, Hengxian YUE
doaj +1 more source
DISCO: Adversarial Defense with Local Implicit Functions [PDF]
, 2022 The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered.
Vasconcelos, Nuno, Ho, Chih-Hui
core