Algorithm 1 Anomalous Model Parameter Detection

01. Server Executes:

02. the global model parameter initialization: $w_0$

03. for iteration round $t=1$ to $I$ do

04.    $C_t\leftarrow$ Randomly choose $N$ clients

05.    for client $n$ in $C_t$ do

06.          $L_{t+1}^n\leftarrow ClientUpdate(n,w_t)$

07.      end for

08.      Client Detection

09.       for each client performing the detection task do

10.                 $r_k\leftarrow$ Return the evaluation results matrix

11.      end for

12.      for $i=1$ to $s$ do

13.           Calculate the penalty coefficient $f_{t+1}^i$

14.      end for

15.         $w_{t+1}\leftarrow \frac{1}{s}{\displaystyle {\sum }_{i=0}^s{f}_{t+1}^i{w}_{t+1}^i}$

16. end for