Results 241 to 250 of about 1,173,800 (295)

A Novel Evasion Attack Against Global Electricity Theft Detectors and a Countermeasure

IEEE Internet of Things Journal, 2023
The smart grid advanced metering infrastructure (AMI) is vulnerable to electricity theft cyber-attacks in which malicious smart meters report low readings to reduce the consumers’ bills.
Mahmoud M. Badr, Mohamed Mahmoud, Mohammed J. Abdulaal, A. Aljohani, F. Alsolami, Abdullah Balamsh   +5 more
semanticscholar   +1 more source

Projective Ranking: A Transferable Evasion Attack Method on Graph Neural Networks

International Conference on Information and Knowledge Management, 2021
Graph Neural Networks (GNNs) have emerged as a series of effective learning methods for graph-related tasks. However, GNNs are shown vulnerable to adversarial attacks, where attackers can fool GNNs into making wrong predictions on adversarial samples ...
He Zhang, Bang Wu, Xiangwen Yang, Chuan Zhou, Shuo Wang, Xingliang Yuan, Shirui Pan   +6 more
semanticscholar   +1 more source

Evasion Attack STeganography: Turning Vulnerability Of Machine Learning To Adversarial Attacks Into A Real-world Application

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
Evasion Attacks have been commonly seen as a weakness of Deep Neural Networks. In this paper, we flip the paradigm and envision this vulnerability as a useful application.
Salah Ghamizi, Maxime Cordy, Mike Papadakis, Y. L. Traon   +3 more
semanticscholar   +1 more source

Distribution-based Adversarial Filter Feature Selection against Evasion Attack

IEEE International Joint Conference on Neural Network, 2021
Feature selection plays an important role in machine learning in order to reduce model complexity and extract more meaningful information. The recent studies indicate that not only the generalization ability but also the security should be considered in ...
P. Chan, Yuanchao Liang, Fei Zhang, D. Yeung   +3 more
semanticscholar   +1 more source

Model Evasion Attack on Intrusion Detection Systems using Adversarial Machine Learning

Annual Conference on Information Sciences and Systems, 2020
Intrusion Detection Systems (IDS) have a long history as an effective network defensive mechanism. The systems alert defenders of suspicious and / or malicious behavior detected on the network.
Md. Ahsan Ayub, William A. Johnson, Douglas A. Talbert, Ambareen Siraj   +3 more
semanticscholar   +1 more source

Learning a Secure Classifier against Evasion Attack

2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), 2016
In security sensitive applications, there is a crafty adversary component which intends to mislead the detection system. The presence of an adversary component conflicts with the stationary data assumption that is a common assumption in most machine learning methods.
Z. Khorshidpour, S. Hashemi, A. Hamzeh
semanticscholar   +2 more sources

Adversarial mRMR against Evasion Attacks

2018 International Joint Conference on Neural Networks (IJCNN), 2018
Machine learning (ML) algorithms provide a good solution for many security sensitive applications, they themselves, however, face the threats of adversary attacks. As a key problem in machine learning, how to design robust feature selection algorithms against these attacks becomes a hot issue.
Miaomiao Wu, Yun Li
openaire   +1 more source

Evasion Attack of Multi-class Linear Classifiers

Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2012
Machine learning has yield significant advances in decision-making for complex systems, but are they robust against adversarial attacks? We generalize the evasion attack problem to the multi-class linear classifiers, and present an efficient algorithm for approximating the optimal disguised instance.
Han Xiao, T. Stibor, C. Eckert
semanticscholar   +2 more sources

Selective Audio Adversarial Example in Evasion Attack on Speech Recognition System

IEEE Transactions on Information Forensics and Security, 2020
Deep neural networks (DNNs) are widely used for image recognition, speech recognition, and other pattern analysis tasks. Despite the success of DNNs, these systems can be exploited by what is termed adversarial examples.
Hyun Kwon, Hyun Kwon, H. Yoon, D. Choi
semanticscholar   +1 more source