Adversarial attacks and adversarial robustness in computational pathology [PDF]
Nature Communications, 2022 Artificial Intelligence can support diagnostic workflows in oncology, but they are vulnerable to adversarial attacks. Here, the authors show that convolutional neural networks are highly susceptible to white- and black-box adversarial attacks in ...
Narmin Ghaffari Laleh +10 more
doaj +7 more sources
Adversarial Robustness with Partial Isometry [PDF]
EntropyDespite their remarkable performance, deep learning models still lack robustness guarantees, particularly in the presence of adversarial examples. This significant vulnerability raises concerns about their trustworthiness and hinders their deployment in ...
Loïc Shi-Garrier +2 more
doaj +8 more sources
Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification [PDF]
Sensors, 2023 Deep neural networks (DNNs) have been known to be vulnerable to adversarial attacks. Adversarial training (AT) is, so far, the only method that can guarantee the robustness of DNNs to adversarial attacks.
Desheng Wang, Weidong Jin, Yunpu Wu
doaj +2 more sources
Improving Adversarial Robustness via Attention and Adversarial Logit Pairing [PDF]
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 +2 more sources
Increasing-Margin Adversarial (IMA) training to improve adversarial robustness of neural networks [PDF]
Computer Methods and Programs in Biomedicine, 2023 Deep neural networks (DNNs) are vulnerable to adversarial noises. Adversarial training is a general and effective strategy to improve DNN robustness (i.e., accuracy on noisy data) against adversarial noises.
Linhai Ma, Liang Liang
exaly +4 more sources
Adversarial robustness assessment: Why in evaluation both L0 and L∞ attacks are necessary [PDF]
PLoS ONE, 2022 There are different types of adversarial attacks and defences for machine learning algorithms which makes assessing the robustness of an algorithm a daunting task.
Shashank Kotyan +1 more
doaj +3 more sources
Machine Learning and Knowledge ExtractionAdversarial training, a widely used technique for fortifying the robustness of machine learning models, has seen its effectiveness further bolstered by modifying loss functions or incorporating additional terms into the training objective.
Sander Joos +4 more
doaj +2 more sources
Towards Adversarial Robustness via Feature Matching [PDF]
IEEE Access, 2020 Image classification systems are known to be vulnerable to adversarial attacks, which are imperceptibly perturbed but lead to spectacularly disgraceful classification.
Zhuorong Li +4 more
doaj +2 more sources
Adversarial Robustness Enhancement for Deep Learning-Based Soft Sensors: An Adversarial Training Strategy Using Historical Gradients and Domain Adaptation [PDF]
SensorsDespite their high prediction accuracy, deep learning-based soft sensor (DLSS) models face challenges related to adversarial robustness against malicious adversarial attacks, which hinder their widespread deployment and safe application.
Runyuan Guo +3 more
doaj +2 more sources
The inherent adversarial robustness of analog in-memory computing [PDF]
Nature CommunicationsA key challenge for deep neural network algorithms is their vulnerability to adversarial attacks. Inherently non-deterministic compute substrates, such as those based on analog in-memory computing, have been speculated to provide significant adversarial ...
Corey Lammie +4 more
doaj +2 more sources