Results 31 to 40 of about 5,389,393 (319)
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection [PDF]
Computer Vision and Pattern Recognition, 2022 Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. However, the problem remains challenging when one tries to generalize the detector to forgeries created by unseen ...
Liang Chen +4 more
semanticscholar +1 more source
Recovery of Adversarial Examples Based on SmsGAN [PDF]
Zhengzhou Daxue xuebao. Gongxue ban, 2021 Due to adversarial examples′ serious interference to the detection models based on deep learning, a recovery method of adversarial examples based on stochastic multihlter statistical generative adversarial network (SmsGAN) was proposed in this work.
ZHAO Junjie, WANG Jinwei
doaj +1 more source
AdvGuard: Fortifying Deep Neural Networks Against Optimized Adversarial Example Attack
IEEE AccessDeep neural networks (DNNs) provide excellent performance in image recognition, speech recognition, video recognition, and pattern analysis. However, they are vulnerable to adversarial example attacks.
Hyun Kwon, Jun Lee
doaj +3 more sources
Natural Adversarial Examples [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 We introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade. The datasets are collected with a simple adversarial filtration technique to create datasets with limited spurious cues. Our datasets' real-world, unmodified examples transfer to various unseen models reliably, demonstrating that ...
Dan Hendrycks +4 more
openaire +2 more sources
Generating adversarial examples without specifying a target model [PDF]
PeerJ Computer Science, 2021 Adversarial examples are regarded as a security threat to deep learning models, and there are many ways to generate them. However, most existing methods require the query authority of the target during their work.
Gaoming Yang +4 more
doaj +2 more sources
LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity [PDF]
European Conference on Computer Vision, 2022 We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional ...
Martin Gubri +4 more
semanticscholar +1 more source
Adversarial example generation with adabelief optimizer and crop invariance [PDF]
Applied intelligence (Boston), 2021 Deep neural networks are vulnerable to adversarial examples, which are crafted by applying small, human-imperceptible perturbations on the original images, so as to mislead deep neural networks to output inaccurate predictions.
Bo Yang +4 more
semanticscholar +1 more source
Clustering Approach for Detecting Multiple Types of Adversarial Examples
Sensors, 2022 With intentional feature perturbations to a deep learning model, the adversary generates an adversarial example to deceive the deep learning model.
Seok-Hwan Choi +3 more
doaj +1 more source
Distinguishability of adversarial examples [PDF]
Proceedings of the 15th International Conference on Availability, Reliability and Security, 2020 Machine learning models can be easily fooled by adversarial examples which are generated from clean examples with small perturbations. This poses a critical challenge to machine learning security, and impedes the wide application of machine learning in many important domains such as computer vision and malware detection. From a unique angle, we propose
Yi Qin, Ryan Hunt, Chuan Yue
openaire +1 more source
Masked Language Model Based Textual Adversarial Example Detection
, 2023 Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Recently, substantial work has shown
Zhang, LY +6 more
core +3 more sources