Results 81 to 90 of about 1,236,597 (154)

Comprehensive comparisons of gradient-based multi-label adversarial attacks

Complex & Intelligent Systems
Adversarial examples which mislead deep neural networks by adding well-crafted perturbations have become a major threat to classification models. Gradient-based white-box attack algorithms have been widely used to generate adversarial examples.
Zhijian Chen, Wenjian Luo, Muhammad Luqman Naseem, Linghao Kong, Xiangkai Yang   +4 more
doaj   +1 more source

Adversarial Ranking Attack and Defense [PDF]

, 2020
Deep Neural Network (DNN) classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this paper, we propose two attacks against deep ranking systems, i.e., Candidate Attack and Query Attack, that can ...
Mo Zhou, Zhenxing Niu, Le Wang 0003, Qilin Zhang 0004, Gang Hua 0001   +4 more
openaire   +2 more sources

Transferable Sparse Adversarial Attack

CoRR, 2021
Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a high attack success rate, prior sparse attack methods achieve a low transferability under the black-box protocol ...
Ziwen He, Wei Wang 0025, Jing Dong 0003, Tieniu Tan   +3 more
openaire   +2 more sources

Multi-Task Adversarial Attack

CoRR, 2020
Deep neural networks have achieved impressive performance in various areas, but they are shown to be vulnerable to adversarial attacks. Previous works on adversarial attacks mainly focused on the single-task setting. However, in real applications, it is often desirable to attack several models for different tasks simultaneously. To this end, we propose
Pengxin Guo 0001, Yuancheng Xu, Baijiong Lin, Yu Zhang 0006   +3 more
openaire   +2 more sources

Rethinking Classifier and Adversarial Attack

CoRR, 2022
Various defense models have been proposed to resist adversarial attack algorithms, but existing adversarial robustness evaluation methods always overestimate the adversarial robustness of these models (i.e., not approaching the lower bound of robustness). To solve this problem, this paper uses the proposed decouple space method to divide the classifier
Youhuan Yang, Lei Sun, Leyu Dai, Song Guo, Xiuqing Mao, Xiaoqin Wang, Bayi Xu   +6 more
openaire   +2 more sources

Adversarial attacks on an oblivious recommender [PDF]

Proceedings of the 13th ACM Conference on Recommender Systems, 2019
Can machine learning models be easily fooled? Despite the recent surge of interest in learned adversarial attacks in other domains, in the context of recommendation systems this question has mainly been answered using hand-engineered fake user profiles. This paper attempts to reduce this gap.
Konstantina Christakopoulou, Arindam Banerjee 0001   +1 more
openaire   +1 more source

Multi-concept adversarial attacks

CoRR, 2021
As machine learning (ML) techniques are being increasingly used in many applications, their vulnerability to adversarial attacks becomes well-known. Test time attacks, usually launched by adding adversarial noise to test instances, have been shown effective against the deployed ML models.
Vibha Belavadi, Yan Zhou 0001, Murat Kantarcioglu, Bhavani M. Thuraisingham   +3 more
openaire   +2 more sources

Link Prediction Adversarial Attack

CoRR, 2018
Deep neural network has shown remarkable performance in solving computer vision and some graph evolved tasks, such as node classification and link prediction. However, the vulnerability of deep model has also been revealed by carefully designed adversarial examples generated by various adversarial attack methods.
Jinyin Chen, Ziqiang Shi, Yangyang Wu, Xuanheng Xu, Haibin Zheng   +4 more
openaire   +2 more sources

LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection [PDF]

IEEE Transactions on Dependable and Secure Computing
Deep learning methods can not only detect false data injection attacks (FDIA) but also locate attacks of FDIA. Although adversarial false data injection attacks (AFDIA) based on deep learning vulnerabilities have been studied in the field of single-label
Jiwei Tian, Chao Shen, Buhong Wang, Xiaofang Xia, Meng Zhang, Chenhao Lin, Qian Li   +6 more
semanticscholar   +1 more source

Deep Reinforcement Learning-Based Adversarial Attack and Defense in Industrial Control Systems

Mathematics
Adversarial attacks targeting industrial control systems, such as the Maroochy wastewater system attack and the Stuxnet worm attack, have caused significant damage to related facilities.
Mun-Suk Kim
doaj   +1 more source