Add a backdoor attack and a label inference attack against VFL

[shgal637]

What type of PR is this?

Uncomment only one /kind <> line, hit enter to put that in a new line, and remove leading whitespaces from that line:

/kind bug

/kind task

/kind feature

What does this PR do / why do we need it:
This PR introduces two new algorithms aimed at enhancing research on the security issues in Vertical Federated Learning (VFL) scenarios:

1. Gradient-Replacement Backdoor Attack: A backdoor attack algorithm that manipulates the gradients to inject malicious behaviors into the server.
2. Direct Label Inference Attack: A label inference algorithm that aims to infer the labels of the data owned by other parties in the VFL setting.
   These additions are crucial for studying and understanding the vulnerabilities and potential defenses in VFL.

Which issue(s) this PR fixes:

Fixes #

Special notes for your reviewers:
The examples folder and the_example.py file are provided as examples. The main code for the algorithms is located in the utils folder.