Algorithm 2 DNN-based IoT attack detection

Require: Dataset $D=\{X,y\}$, learning rate ${\eta }_0$, batch size B, epochs E, learning decay $\lambda$, folds K

Ensure: Trained model $\mathcal{M}$, results $\mathcal{R}$

1: Normalize features: $x^{\prime }={\displaystyle \frac{x-x_{min}}{x_{max}-x_{min}}},\forall x\in X$

2: Initialize weights $W,b\sim \mathcal{N}(0,{\sigma }^2)$

3: Initialize result set $\mathcal{R}\leftarrow \varnothing$

4: $F\leftarrow$ Stratified K-fold split on $(X,y)$

5: for all $(X_{\mathrm{train}},y_{\mathrm{train}},X_{\mathrm{test}},y_{\mathrm{test}})\in F$ do

6:     Apply SMOTE: $(X_{\mathrm{train}}^{\mathrm{res}},y_{\mathrm{train}}^{\mathrm{res}})\leftarrow \mathrm{SMOTE}(X_{\mathrm{train}},y_{\mathrm{train}})$

7:     $\eta \leftarrow {\eta }_0$

8:     for $e=1$ to E do

9:         Shuffle$(X_{\mathrm{train}}^{\mathrm{res}},y_{\mathrm{train}}^{\mathrm{res}})$

10:         for all $B_i=(X_B,y_B)\subset (X_{\mathrm{train}}^{\mathrm{res}},y_{\mathrm{train}}^{\mathrm{res}})$ do

11:              $Z=W{X}_B+b$

12:              $A=max(0,Z)$

13:              $\tilde{A}=\mathrm{Dropout}(A,p)$

14:              $\widehat{y}=\mathrm{Softmax}\left(\tilde{A}\right)$

15:              $L=-{\sum }_{i=1}^N{y}_{i}log\left({\widehat{y}}_i\right)$

16:              $W\leftarrow W-\eta {\displaystyle \frac{\partial L}{\partial W}},b\leftarrow b-\eta {\displaystyle \frac{\partial L}{\partial b}}$

17:         end for

18:         $\eta \leftarrow {\eta }_0\times {\lambda }^{{\displaystyle \frac{e}{E}}}$

19:         ${\mathcal{R}}_e\leftarrow \mathrm{Evaluate}(\mathcal{M},X_{\mathrm{test}},y_{\mathrm{test}})$

20:         if EarlyStopping(${\mathcal{R}}_e$) then

21:              Break

22:         end if

23:     end for

24:     Append ${\mathcal{R}}_e$ to $\mathcal{R}$

25: end for

26: return $\mathcal{M},\mathcal{R}$