Robust Adversarial Example Detection Algorithm Based on High-Level Feature Differences [PDF]
SensorsThe threat posed by adversarial examples (AEs) to deep learning applications has garnered significant attention from the academic community. In response, various defense strategies have been proposed, including adversarial example detection.
Hua Mu +4 more
doaj +5 more sources
A Novel Adversarial Example Detection Method Based on Frequency Domain Reconstruction for Image Sensors [PDF]
SensorsConvolutional neural networks (CNNs) have been extensively used in numerous remote sensing image detection tasks owing to their exceptional performance.
Shuaina Huang, Zhiyong Zhang, Bin Song
doaj +3 more sources
Dual-Domain Adaptive Input Perturbation Sensitivity for Adversarial Example Detection [PDF]
SensorsVision-sensor-based intelligent perception systems are increasingly used in safety-critical scenarios such as autonomous driving, edge surveillance, and Internet-of-Things (IoT) platforms. The vulnerability of deep neural networks to adversarial examples
Li Yue +4 more
doaj +3 more sources
A Review of Adversarial Example Detection in IoT Sensor Networks: Methods, Evaluation, and Edge Deployment Constraints [PDF]
SensorsDeep learning has been widely deployed in critical scenarios such as the Internet of Things (IoT), industrial sensing, network intrusion detection, and cyber-physical system monitoring, where model inference directly affects system security, operational ...
Wenqiang Xu, Jian Li
doaj +3 more sources
A Cascade Model-Aware Generative Adversarial Example Detection Method
Tsinghua Science and Technology, 2021 Deep Neural Networks (DNNs) are demonstrated to be vulnerable to adversarial examples, which are elaborately crafted to fool learning models. Since the accuracy and robustness of DNNs are at odds for the adversarial training method, the adversarial ...
Keji Han, Yun Li, Bin Xia
doaj +3 more sources
Hybrid reverse knowledge distillation for adversarial example detection [PDF]
Scientific ReportsDeep neural networks have achieved remarkable success in various computer vision tasks, yet they remain vulnerable to adversarial examples—carefully crafted perturbations that are imperceptible to humans but cause misclassification.
Hyun Kwon, Joo Bon Maeng, Dae-Jin Kim
doaj +2 more sources
Securing IoT Vision Systems: An Unsupervised Framework for Adversarial Example Detection Integrating Spatial Prototypes and Multidimensional Statistics [PDF]
SensorsThe deployment of deep learning models in Internet of Things (IoT) systems is increasingly threatened by adversarial attacks. To address the challenge of effectively detecting adversarial examples generated by Generative Adversarial Networks (AdvGANs ...
Naile Wang +3 more
doaj +2 more sources
Evading Logits-Based Detections to Audio Adversarial Examples by Logits-Traction Attack
Applied Sciences, 2022 Automatic Speech Recognition (ASR) provides a new way of human-computer interaction. However, it is vulnerable to adversarial examples, which are obtained by deliberately adding perturbations to the original audios.
Songshen Han +4 more
doaj +3 more sources
Adversarial Examples Detection Method Based on Image Denoising and Compression [PDF]
Jisuanji gongcheng, 2023 Numerous deep learning achievements in the field of computer vision have been widely applied in real life. However, adversarial examples can lead to false positives in deep learning models with high confidence, resulting in serious security consequences.
Feiyu WANG, Fan ZHANG, Jiayu DU, Hongle LEI, Xiaofeng QI
doaj +1 more source
Adversarial Examples Detection Beyond Image Space [PDF]
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021 To appear in ICASSP ...
Kejiang Chen +6 more
openaire +3 more sources