Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Adversarial attacks and defenses in wind power forecasting system.

More »

Fig 1 Expand

Table 1.

Structure of the forecasting model.

More »

Table 1 Expand

Fig 2.

Structure of the LSTM layer.

More »

Fig 2 Expand

Table 2.

Structure of the substitute model.

More »

Table 2 Expand

Table 3.

Structure of DAE.

More »

Table 3 Expand

Fig 3.

Structure of the DAE defense model.

More »

Fig 3 Expand

Fig 4.

Performance of the DC-MI-FGSM attack algorithm under different momentum decay factors across different attack scenarios.

More »

Fig 4 Expand

Fig 5.

Adversarial attacks on wind power forecasting under the white-box scenario.

(a) Impact of DC-MI-FGSM () on the forecast curves when . (b) Impact of DC-MI-FGSM () on the forecast curves when .

More »

Fig 5 Expand

Table 4.

Forecast errors of different attack methods under varying perturbation strengths in the white-box environment.

More »

Table 4 Expand

Fig 6.

Stealthiness comparison of DC-MI-FGSM, FGSM, PGD, and MI-FGSM in the white-box environment.

(a) APP of adversarial samples under different attacks when . (b) APP of adversarial samples under different attacks when .

More »

Fig 6 Expand

Fig 7.

Adversarial attacks on wind power forecasting under the black-box scenario.

(a) Impact of DC-MI-FGSM () on the forecast curves when . (b) Impact of DC-MI-FGSM () on the forecast curves when .

More »

Fig 7 Expand

Table 5.

Forecast errors of different attack methods under varying perturbation strengths in the black-box environment.

More »

Table 5 Expand

Fig 8.

Stealthiness comparison of DC-MI-FGSM, FGSM, PGD, and MI-FGSM in the black-box environment.

(a) APP of adversarial samples under different attacks when . (b) APP of adversarial samples under different attacks when .

More »

Fig 8 Expand

Fig 9.

Comparison of defense performance between DAE and AT in the white-box environment.

(a) MAPE reduction of the attacked forecasting model under different defense strategies when ; (b) MAPE reduction of the attacked forecasting model under different defense strategies when .

More »

Fig 9 Expand

Fig 10.

Defense performance of DAE against the DC-MI-FGSM white-box attacks.

(a) Restoration of the attacked forecast curve under the DAE defense when . (b) Restoration of the attacked forecast curve under the DAE defense when .

More »

Fig 10 Expand

Table 6.

Forecast errors of the forecasting model with defense algorithms.

More »

Table 6 Expand

Fig 11.

Comparison of defense performance between DAE and AT in the black-box environment.

(a) MAPE reduction of the attacked forecasting model under different defense strategies when ; (b) MAPE reduction of the attacked forecasting model under different defense strategies when .

More »

Fig 11 Expand

Fig 12.

Defense performance of DAE against the DC-MI-FGSM black-box attacks.

(a) Restoration of the attacked forecast curve under the DAE defense when . (b) Restoration of the attacked forecast curve under the DAE defense when .

More »

Fig 12 Expand