Results 31 to 40 of about 3,276,744 (244)

Black-box attacks and defense for DNN-based power quality classification in smart grid

Energy Reports, 2022
Machine learning (ML) models are widely used in smart grid, but they are vulnerable to adversarial examples that are maliciously crafted using the input data. Therefore, the use of these models in smart grid can cause significant damage.
Liangheng Zhang, Congmei Jiang, Aiping Pang   +2 more
doaj   +1 more source

Black-Box Adversarial Attack on Time Series Classification

, 2023
With the increasing use of deep neural network (DNN) in time series classification (TSC), recent work reveals the threat of adversarial attack, where the adversary can construct adversarial examples to cause model mistakes.
Huang, Yuanmin, Yang, Min, Zhang, Mi, Feng, Fuli, Ding, Daizong, Jiang, Erling   +5 more
core   +1 more source

Boosting Targeted Black-Box Attacks via Ensemble Substitute Training and Linear Augmentation

Applied Sciences, 2019
These years, Deep Neural Networks (DNNs) have shown unprecedented performance in many areas. However, some recent studies revealed their vulnerability to small perturbations added on source inputs.
Xianfeng Gao, Yu-an Tan, Hongwei Jiang, Quanxin Zhang, Xiaohui Kuang   +4 more
doaj   +1 more source

PCA-based membership inference attack for machine learning models

Tongxin xuebao, 2022
Aiming at the problem of restricted access failure in current black box membership inference attacks, a PCA-based membership inference attack was proposed.Firstly, in order to solve the restricted access problem of black box membership inference attacks,
Changgen PENG, Ting GAO, Huilan LIU, Hongfa DING   +3 more
doaj   +2 more sources

Adversarial Attacks and Defense in Deep Reinforcement Learning (DRL)-Based Traffic Signal Controllers

IEEE Open Journal of Intelligent Transportation Systems, 2021
Security attacks on intelligent transportation systems (ITS) may result in life-threatening situations. Combining deep neural networks with reinforcement learning (RL) models called DRL shows promising results when applied to urban Traffic Signal Control
Ammar Haydari, Michael Zhang, Chen-Nee Chuah   +2 more
doaj   +1 more source

A Hybrid Adversarial Attack for Different Application Scenarios

Applied Sciences, 2020
Adversarial attack against natural language has been a hot topic in the field of artificial intelligence security in recent years. It is mainly to study the methods and implementation of generating adversarial examples. The purpose is to better deal with
Xiaohu Du, Jie Yu, Zibo Yi, Shasha Li, Jun Ma, Yusong Tan, Qinbo Wu   +6 more
doaj   +1 more source

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack

, 2022
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.
Tang, Ke, Li, Qing, Dai, Zeyu, Liu, Shengcai   +3 more
core  

Boosting Adversarial Transferability with Shallow-Feature Attack on SAR Images

Remote Sensing, 2023
Adversarial example generation on Synthetic Aperture Radar (SAR) images is an important research area that could have significant impacts on security and environmental monitoring.
Gengyou Lin, Zhisong Pan, Xingyu Zhou, Yexin Duan, Wei Bai, Dazhi Zhan, Leqian Zhu, Gaoqiang Zhao, Tao Li   +8 more
doaj   +1 more source

Functional comparison of EncB and EncC cargo proteins in iron storage within the Myxococcus xanthus encapsulin

FEBS Letters, EarlyView.
Encapsulins are protein nanocompartments that play an important role in iron storage. In the Myxococcus xanthus encapsulin system, two cargo proteins called EncB and EncC contribute to iron mineralization. Here, we show that EncB and EncC generate iron‐containing minerals with distinct chemical compositions, suggesting that the composition of stored ...
Harry B. McDowell, Thomas Walther, Egbert Hoiczyk   +2 more
wiley   +1 more source

A comprehensive transplanting of black-box adversarial attacks from multi-class to multi-label models

Complex & Intelligent Systems
Adversarial examples generated by perturbing raw data with carefully designed, imperceptible noise have emerged as a primary security threat to artificial intelligence systems.
Zhijian Chen, Qi Zhou, Yujiang Liu, Wenjian Luo   +3 more
doaj   +1 more source