Results 101 to 110 of about 1,236,597 (154)

Distillation-Based Cross-Model Transferable Adversarial Attack for Remote Sensing Image Classification

Remote Sensing
Deep neural networks have achieved remarkable performance in remote sensing image (RSI) classification tasks. However, they remain vulnerable to adversarial attack.
Xiyu Peng, Jingyi Zhou, Xiaofeng Wu
doaj   +1 more source

Recovering Localized Adversarial Attacks [PDF]

, 2019
Deep convolutional neural networks have achieved great successes over recent years, particularly in the domain of computer vision. They are fast, convenient, and -- thanks to mature frameworks -- relatively easy to implement and deploy. However, their reasoning is hidden inside a black box, in spite of a number of proposed approaches that try to ...
Göpfert, Jan Philip, Wersing, Heiko, Hammer, Barbara, Tetko, Igor V., Kůrková, Věra, Karpov, Pavel, Theis, Fabian   +6 more
openaire   +3 more sources

DIPA: Adversarial Attack on DNNs by Dropping Information and Pixel-Level Attack on Attention

Information
Deep neural networks (DNNs) have shown remarkable performance across a wide range of fields, including image recognition, natural language processing, and speech processing. However, recent studies indicate that DNNs are highly vulnerable to well-crafted
Jing Liu, Huailin Liu, Pengju Wang, Yang Wu, Keqin Li   +4 more
doaj   +1 more source

Black-Box Universal Adversarial Attack for DNN-Based Models of SAR Automatic Target Recognition

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep neural networks (DNNs) are vulnerable to attacks of adversarial examples. Universal adversarial attack algorithms can help evaluate and improve the robustness of the SAR-
Xuanshen Wan, Wei Liu, Chaoyang Niu, Wanjie Lu, Meng Du, Yuanli Li   +5 more
doaj   +1 more source

Adversarial Attacks on Hyperbolic Networks

As hyperbolic deep learning grows in popularity, so does the need for adversarial robustness in the context of such a non-Euclidean geometry. To this end, this paper proposes hyperbolic alternatives to the commonly used FGM and PGD adversarial attacks.
Max van Spengler, Jan Zahálka, Pascal Mettes   +2 more
openaire   +2 more sources

Research on adversarial attack and defense of photovoltaic power prediction

Dianzi Jishu Yingyong
Deep neural networks have been widely used in photovoltaic power prediction, but they are vulnerable to adversarial attacks. In order to improve the robustness of the prediction model, an adversarial attack algorithm based on fast gradient sign method ...
Zhou Wang
doaj   +1 more source

Adversarial Attacks Against World Models: Hallucination-Driven Policy Failure

Applied Sciences
World models have demonstrated powerful environment modeling capabilities in scenarios such as autonomous driving and robotics, but their adversarial security issues remain underexplored, in particular, adversarial risk analysis of world models.
Junjian Zhang, Hao Tan, Ruonan Li, Aiping Li, Zhaoquan Gu   +4 more
doaj   +1 more source

DLSF:A Textual Adversarial Attack Method Based on Dual-level Semantic Filtering [PDF]

Jisuanji kexue
In the field of commercial applications,deep learning-based text models play a crucial role but are also susceptible to adversarial samples,such as the incorporation of confusing vocabulary into reviews leading to erroneous model responses.A strong ...
XIONG Xi, DING Guangzheng, WANG Juan, ZHANG Shuai
doaj   +1 more source

Adversarial Attacks on Variational Autoencoders

CoRR, 2018
Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We assess --- with statistically validated experiments --- the resistance to attacks of three variational ...
George Gondim-Ribeiro, Pedro Tabacof, Eduardo Valle   +2 more
openaire   +2 more sources

Adversarial Attacks on Data Attribution

CoRR
Accepted at the 13th International Conference on Learning Representations (ICLR 2025)
Xinhe Wang 0001, Pingbang Hu, Junwei Deng, Jiaqi W. Ma   +3 more
openaire   +3 more sources