Results 21 to 30 of about 5,389,393 (319)
Smooth adversarial examples [PDF]
EURASIP Journal on Information Security, 2020 This paper investigates the visual quality of the adversarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artifacts.
Hanwei Zhang +3 more
doaj +4 more sources
Adversarial examples in the physical world [PDF]
International Conference on Learning Representations, 2016 Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to ...
Alexey Kurakin +2 more
semanticscholar +5 more sources
Enhancing Adversarial Example Transferability With an Intermediate Level Attack [PDF]
IEEE International Conference on Computer Vision, 2019 Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model.
Qian Huang +5 more
semanticscholar +2 more sources
Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks [PDF]
arXiv.org, 2023 Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models.
Tianrui Qin +4 more
semanticscholar +3 more sources
DroidEnemy: Battling adversarial example attacks for Android malware detection
Digital Communications and Networks, 2022 In recent years, we have witnessed a surge in mobile devices such as smartphones, tablets, smart watches, etc., most of which are based on the Android operating system. However, because these Android-based mobile devices are becoming increasingly popular,
Neha Bala +5 more
doaj +2 more sources
Adversarial Example Soups: Improving Transferability and Stealthiness for Free [PDF]
IEEE Transactions on Information Forensics and SecurityTransferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing transferability is to keep only the optimal adversarial example from all ...
Bo Yang +6 more
semanticscholar +3 more sources
IEEE Access, 2019 Deep neural networks (DNNs) have useful applications in machine learning tasks involving recognition and pattern analysis. Despite the favorable applications of DNNs, these systems can be exploited by adversarial examples.
Hyun Kwon +3 more
doaj +2 more sources
Approaching Adversarial Example Classification with Chaos Theory. [PDF]
Entropy (Basel), 2020 Adversarial examples are one of the most intriguing topics in modern deep learning. Imperceptible perturbations to the input can fool robust models. In relation to this problem, attack and defense methods are being developed almost on a daily basis.
Pedraza A, Deniz O, Bueno G.
europepmc +2 more sources
Research on Image Adversarial Example Generation Method Based on SE-AdvGAN [PDF]
Jisuanji gongchengAdversarial examples are crucial for evaluating the robustness of Deep Neural Network (DNN) and revealing their potential security risks. The adversarial example generation method based on a Generative Adversarial Network (GAN), AdvGAN, has made ...
ZHAO Hong, SONG Furong, LI Wengai
doaj +2 more sources
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples [PDF]
International Conference on Machine Learning, 2023 Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style.
Chumeng Liang +8 more
semanticscholar +1 more source