Results 21 to 30 of about 8,712 (199)
Patch-wise++ Perturbation for Adversarial Targeted Attacks
CoRR, 2020 Although great progress has been made on adversarial attacks for deep neural networks (DNNs), their transferability is still unsatisfactory, especially for targeted attacks. There are two problems behind that have been long overlooked: 1) the conventional setting of $T$ iterations with the step size of $ε/T$ to comply with the $ε$-constraint.
Lianli Gao +3 more
openaire +2 more sources
Generalized Grad-CAM attacking method based on adversarial patch
Tongxin xuebao, 2021 To verify the fragility of the Grad-CAM, a Grad-CAM attack method based on adversarial patch was proposed.By adding a constraint to the Grad-CAM in the classification loss function, an adversarial patch could be optimized and the adversarial image could ...
Nianwen SI +5 more
doaj +2 more sources
Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings
2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2023 To appear in APSIPA ASC ...
AprilPyone MaungMaung +2 more
openaire +2 more sources
Remote Sensing, 2023 Deep learning (DL) models have recently been widely used in UAV aerial image semantic segmentation tasks and have achieved excellent performance. However, DL models are vulnerable to adversarial examples, which bring significant security risks to safety ...
Zhen Wang +3 more
doaj +1 more source
Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact
, 2023 This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very powerful and pre-trained CNN models working very accurately on image datasets for image classification tasks may ...
Jaydip Sen, Subhasis Dasgupta
openaire +2 more sources
Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches
Sensors, 2021 Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack,
Yongsu Kim +5 more
doaj +1 more source
Adversarial Reprogramming of Text Classification Neural Networks [PDF]
, 2019 Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network.
Dubnov, Shlomo +3 more
core +2 more sources
Camouflaged Adversarial Patch Attack on Object Detector
Journal of the Korea Institute of Military Science and Technology, 2023 Adversarial attacks have received great attentions for their capacity to distract state-of-the-art neural networks by modifying objects in physical domain. Patch-based attack especially have got much attention for its optimization effectiveness and feasible adaptation to any objects to attack neural network-based object detectors.
Jeonghun Kim, Hunmin Yang, Se-Yoon Oh
openaire +1 more source
Care and COVID 19: Lessons for liberals and neoliberals
Child &Family Social Work, EarlyView., 2023 Abstract Within the liberal political traditions, care is regarded as a private matter, a problem of ethics rather than justice. Social justice is framed as an issue of economics (re/distribution), culture (recognition) and/or politics (representation).
Kathleen Lynch
wiley +1 more source
Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks
, 2020 Deep neural networks (DNN) are known to be vulnerable to adversarial attacks. Numerous efforts either try to patch weaknesses in trained models, or try to make it difficult or costly to compute adversarial examples that exploit them.
Li, Bo +5 more
core +1 more source