Super-efficient detector and defense method for adversarial attacks in power quality classification

The correct classification of power quality (PQ) is the key step to ensure the normal operation of smart grid. Deep neural networks have been widely used for PQ classification, but they face serious threats from adversarial attacks. At present, there are few studies on defense algorithms for adversa...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Applied energy Ročník 361; s. 122872
Hlavní autori: Zhang, Liangheng, Jiang, Congmei, Pang, Aiping, He, Yu
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.05.2024
Predmet:
Adversarial attack
Deep neural network
electrical equipment
energy
memory
Multi-source feature adversarial training
Multi-source feature detector
Power quality
Smart grid
NN
MSFD
Multi-source feature detector
PQ
ANN
CNN
FGSM-variant
DNN
LR
CNN-LSTM
TAT
CPS
SVM
GRU
BN
AUC
DS
DT
PNN
Adversarial attack
SNR
KD
ReLu
Multi-source feature adversarial training
MLD-AE
FFNN
SSA
PQD
LSTM
LID
DAE
PGD
Smart grid
MSFAT
Deep neural network
SAA
ANA
Power quality
FDIA
DDAE
FGSM
ISSN:0306-2619
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The correct classification of power quality (PQ) is the key step to ensure the normal operation of smart grid. Deep neural networks have been widely used for PQ classification, but they face serious threats from adversarial attacks. At present, there are few studies on defense algorithms for adversarial attacks in PQ classification. Furthermore, detection algorithms have not yet been studied. In order to solve the above problems, we first use Convolutional Neural Network-Long Short-Term Memory Network (CNN-LSTM) to classify PQ signals. Four representative adversarial attack algorithms (i.e., FGSM, FGSM-variant, PGD and SSA) in PQ classification are compared and summarized from three aspects: average running time of attack, robustness of attack and classification accuracy of attacked model. Second, we propose a Multi-Source Feature Detector (MSFD) to detect adversarial attacks. The model architecture of MSFD is a binary classification model based on CNN. The detection function can be implemented simply by placing MSFD in front of the classification model. Third, we propose a Multi-Source Feature Adversarial Training (MSFAT) to defend against adversarial attacks. The experimental results demonstrate the effectiveness and superiority of the proposed methods. MSFD can detect the above four representative adversarial attacks with an extremely high recognition rate, and MSFAT can significantly improve the classification accuracy of the attacked model under these attacks. MSFD and MSFAT can effectively deal with adversarial attacks in different environments without any adjustment. Compared with the most advanced adversarial training defense method in PQ classification, the proposed MSFAT can overcome the drawback that adversarial training may reduce the classification accuracy of the attacked model and is significantly effective for multiple adversarial attacks in PQ classification. •The security of power quality classification is studied from three aspects: adversarial attack, detection and defense.•Four representative adversarial attack algorithms in power quality classification are compared and summarized.•A Multi-Source Feature Detector algorithm for detecting adversarial attacks is proposed.•A Multi-Source Feature Adversarial Training algorithm for defending against adversarial attacks is proposed.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0306-2619
DOI:10.1016/j.apenergy.2024.122872