Results 11 to 20 of about 7,756 (262)
Attacking Adversarial Attacks as A Defense
CoRR, 2021 It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.
Boxi Wu +8 more
openaire +2 more sources
Adversarial Attack with Raindrops
CoRR, 2023 10 pages, 7 figures, This manuscript was submitted to CVPR ...
Jiyuan Liu 0005 +4 more
openaire +2 more sources
Stochastic sparse adversarial attacks [PDF]
2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI), 2021 This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (NNC). SSAA offer new examples of sparse (or $L_0$) attacks for which only few methods have been proposed previously.
Hajri, Hatem +4 more
openaire +4 more sources
Adversarial attacks and defenses in deep learning
网络与信息安全学报, 2020 The adversarial example is a modified image that is added imperceptible perturbations, which can make deep neural networks decide wrongly. The adversarial examples seriously threaten the availability of the system and bring great security risks to the ...
LIU Ximeng +2 more
doaj +3 more sources
Remote Sensing, 2023 Aerial Image Semantic segmentation based on convolution neural networks (CNNs) has made significant process in recent years. Nevertheless, their vulnerability to adversarial example attacks could not be neglected.
Zhen Wang +3 more
doaj +1 more source
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML system. However, manual selection of attackers tends to be sub-optimal, leading to a mistakenly assessment of model ...
Xiaofeng Mao +5 more
openaire +2 more sources
TextFirewall: Omni-Defending Against Adversarial Texts in Sentiment Classification
IEEE Access, 2021 Sentiment classification has been broadly applied in real life, such as product recommendation and opinion-oriented analysis. Unfortunately, the widely employed sentiment classification systems based on deep neural networks (DNNs) are susceptible to ...
Wenqi Wang +3 more
doaj +1 more source
CoRR, 2022 ICML Workshop 2022 on Adversarial Machine Learning ...
Soichiro Kumano +2 more
openaire +2 more sources
GANBA: Generative Adversarial Network for Biometric Anti-Spoofing
Applied Sciences, 2022 Automatic speaker verification (ASV) is a voice biometric technology whose security might be compromised by spoofing attacks. To increase the robustness against spoofing attacks, presentation attack detection (PAD) or anti-spoofing systems for detecting ...
Alejandro Gomez-Alanis +2 more
doaj +1 more source
Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
IEEE Access, 2020 Deep Neural Networks (DNNs) classifiers performance degrades under adversarial attacks, such attacks are indistinguishably perturbed relative to the original data.
Benjamin Appiah +4 more
doaj +1 more source