paper-with-me

홈 › Papers

Generating Minimal Adversarial Perturbations with Integrated Adaptive Gradients

2019-04-12 · Yatie Xiao, Chi-Man Pun

Deep neural networks are easily fooled high confidence predictions for adversarial samples

📄 PDF Abstract BibTeX arXiv:1904.06186

Code (0)

등록된 구현이 없습니다.

Tasks

Image Classification

Similar Papers 제목 키워드 기반

Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach

2024-04-25 · Cristopher McIntyre-Garcia, Adrien Heymans, Beril Borali, Won-Sook Lee 외

Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algorithm for evaluating the robustness of obj…

Objectobject-detectionObject Detection

Adaptive Perturbation for Adversarial Attack

2021-11-27 · Zheng Yuan, Jie Zhang, Zhaoyan Jiang, Liangliang Li 외

In recent years, the security of deep learning models achieves more and more attentions with the rapid development of neural networks, which are vulnerable to adversarial examples. Almost all existing gradient-based atta…

Adversarial Attack

Adaptive Generation of Unrestricted Adversarial Inputs

2019-05-07 · Isaac Dunn, Hadrien Pouget, Tom Melham, Daniel Kroening

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is …

ExploreADV: Towards exploratory attack for Neural Networks

2023-01-01 · Tianzuo Luo, Yuyi Zhong, Siaucheng Khoo

Although deep learning has made remarkable progress in processing various types of data such as images, text and speech, they are known to be susceptible to adversarial perturbations: perturbations specifically designed …

Adversarial Attack

IWA: Integrated Gradient based White-box Attacks for Fooling Deep Neural Networks

2021-02-03 · Yixiang Wang, Jiqiang Liu, Xiaolin Chang, Jelena Mišić 외

The widespread application of deep neural network (DNN) techniques is being challenged by adversarial examples, the legitimate input added with imperceptible and well-designed perturbations that can fool DNNs easily in t…

DNN Testing