Results 71 to 80 of about 173,113 (165)
Spatially Transformed Adversarial Examples
, 2018 Recent studies show that widely used deep neural networks (DNNs) are vulnerable to carefully crafted adversarial examples. Many advanced algorithms have been proposed to generate adversarial examples by leveraging the $\mathcal{L}_p$ distance for penalizing perturbations.
Xiao, Chaowei +5 more
openaire +2 more sources
A survey of practical adversarial example attacks
Cybersecurity, 2018 Adversarial examples revealed the weakness of machine learning techniques in terms of robustness, which moreover inspired adversaries to make use of the weakness to attack systems employing machine learning.
Lu Sun, Mingtian Tan, Zhe Zhou
doaj +1 more source
Detecting Adversarial Examples
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples. While numerous successful adversarial attacks have been proposed, defenses against these attacks remain relatively understudied. Existing defense approaches either focus on negating the effects of perturbations caused by the attacks to restore the DNNs' original ...
Mumcu, Furkan, Yilmaz, Yasin
openaire +2 more sources
Generating Natural Adversarial Examples
, 2017 Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in substantially different model predictions, is helpful in evaluating the robustness of these models by exposing the ...
Zhao, Zhengli +2 more
openaire +2 more sources
Adversarial Examples in the Physical World [PDF]
, 2018 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 misclassify it.
Kurakin, Alexey +2 more
openaire +2 more sources
Synthesizing Robust Adversarial Examples
, 2017 Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems.
Athalye, Anish +3 more
openaire +2 more sources
Adversarial Examples for CNN-Based Malware Detectors
IEEE Access, 2019 The convolutional neural network (CNN)-based models have achieved tremendous breakthroughs in many end-to-end applications, such as image identification, text classification, and speech recognition.
Bingcai Chen +4 more
doaj +1 more source
Adversarial Examples and Metrics
, 2020 25 pages, 1 figure, under submission, fixe typos from previous ...
Döttling, Nico +3 more
openaire +2 more sources
Cross-Gen: An Efficient Generator Network for Adversarial Attacks on Cross-Modal Hashing Retrieval
Future InternetResearch on deep neural network (DNN)-based multi-dimensional data visualization has thoroughly explored cross-modal hash retrieval (CMHR) systems, yet their vulnerability to malicious adversarial examples remains evident.
Chao Hu +7 more
doaj +1 more source
Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constraint), suitable for interpreting the vulnerability of DNNs. However, existing solutions fail to yield interpretable adversarial examples due to their poor sparsity. Worse still,
Lin, Fudong +4 more
openaire +2 more sources