Results 41 to 50 of about 5,561,446 (302)
Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
Frontiers in Artificial Intelligence, 2022 Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques for defending
Xingjian Li +4 more
doaj +1 more source
Not all adversarial examples require a complex defense : identifying over-optimized adversarial examples with IQR-based logit thresholding [PDF]
, 2019 Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point ...
De Neve, Wesley +2 more
core +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 +1 more source
A Robust Adversarial Example Attack Based on Video Augmentation
Applied Sciences, 2023 Despite the success of learning-based systems, recent studies have highlighted video adversarial examples as a ubiquitous threat to state-of-the-art video classification systems.
Mingyong Yin +3 more
doaj +1 more source
Adversarial Examples: Opportunities and Challenges [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2019 16 pages, 13 figures, 5 ...
Jiliang Zhang, Chen Li
openaire +3 more sources
Really natural adversarial examples [PDF]
International Journal of Machine Learning and Cybernetics, 2021 AbstractThe phenomenon of Adversarial Examples has become one of the most intriguing topics associated to deep learning. The so-called adversarial attacks have the ability to fool deep neural networks with inappreciable perturbations. While the effect is striking, it has been suggested that such carefully selected injected noise does not necessarily ...
Anibal Pedraza +2 more
openaire +1 more source
Adversarial Examples for Generative Models [PDF]
2018 IEEE Security and Privacy Workshops (SPW), 2018 We explore methods of producing adversarial examples on deep generative models such as the variational autoencoder (VAE) and the VAE-GAN. Deep learning architectures are known to be vulnerable to adversarial examples, but previous work has focused on the application of adversarial examples to classification tasks.
Kos, Jernej, Fischer, Ian, Song, Dawn
openaire +2 more sources
Boundary Adversarial Examples Against Adversarial Overfitting
, 2022 Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have been reported, i.e., memorization effects induced by large loss data or because of small loss data and growing ...
Hameed, Muhammad Zaid, Buesser, Beat
openaire +2 more sources
Adversarial examples in remote sensing [PDF]
Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2018 This paper considers attacks against machine learning algorithms used in remote sensing applications, a domain that presents a suite of challenges that are not fully addressed by current research focused on natural image data such as ImageNet. In particular, we present a new study of adversarial examples in the context of satellite image classification
Czaja, Wojciech +4 more
openaire +2 more sources
Optimized Adversarial Example With Classification Score Pattern Vulnerability Removed
IEEE Access, 2022 Neural networks provide excellent service on recognition tasks such as image recognition and speech recognition as well as for pattern analysis and other tasks in fields related to artificial intelligence.
Hyun Kwon, Kyoungmin Ko, Sunghwan Kim
doaj +1 more source