Results 11 to 20 of about 27,717 (260)
Smooth adversarial examples [PDF]
EURASIP Journal on Information Security, 2020 AbstractThis paper investigates the visual quality of the adversarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artifacts. In this work, smoothing has a different meaning as it perceptually shapes the perturbation according to the visual content of the image to be attacked. The perturbation becomes locally
Zhang, Hanwei +3 more
openaire +5 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
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
Verifying the Causes of Adversarial Examples [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in examining a high-dimensional image space thoroughly, research on explaining and justifying the causes of adversarial ...
Li, H +4 more
openaire +3 more sources
Efficient Adversarial Training With Transferable Adversarial Examples [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost of generating strong adversarial examples during training.
Haizhong Zheng +4 more
openaire +2 more sources
A Universal Detection Method for Adversarial Examples and Fake Images
Sensors, 2022 Deep-learning technologies have shown impressive performance on many tasks in recent years. However, there are multiple serious security risks when using deep-learning technologies. For examples, state-of-the-art deep-learning technologies are vulnerable
Jiewei Lai +3 more
doaj +1 more source
Semantic Adversarial Examples [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018 Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the model prediction error.
Hossein Hosseini, Radha Poovendran
openaire +2 more sources
Entropy, 2022 Deep neural networks in the area of information security are facing a severe threat from adversarial examples (AEs). Existing methods of AE generation use two optimization models: (1) taking the successful attack as the objective function and limiting perturbations as the constraint; (2) taking the minimum of adversarial perturbations as the target and
Du, Zhenyu, Liu, Fangzheng, Yan, Xuehu
openaire +3 more sources
Adversarial examples for models of code [PDF]
Proceedings of the ACM on Programming Languages, 2020 Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples , and introduce a novel approach for attacking trained models of code using ...
Noam Yefet, Uri Alon 0002, Eran Yahav
openaire +2 more sources