Update app.py
Browse files
app.py
CHANGED
|
@@ -625,6 +625,47 @@ with demo:
|
|
| 625 |
# </p>
|
| 626 |
# """
|
| 627 |
# )
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 628 |
gr.Markdown(
|
| 629 |
f"""
|
| 630 |
<p align="center">
|
|
@@ -634,6 +675,31 @@ with demo:
|
|
| 634 |
)
|
| 635 |
|
| 636 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 637 |
########################## Key Gen Part ##########################
|
| 638 |
|
| 639 |
gr.Markdown(
|
|
@@ -910,6 +976,20 @@ demo.launch(share=False)
|
|
| 910 |
# # </p>
|
| 911 |
# # """
|
| 912 |
# # )
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 913 |
# with gr.Row():
|
| 914 |
# with gr.Column(elem_id="center_column"):
|
| 915 |
# gr.Image("Img/schema.png", width=200, show_label=False)
|
|
|
|
| 625 |
# </p>
|
| 626 |
# """
|
| 627 |
# )
|
| 628 |
+
|
| 629 |
+
with gr.Accordion("What is bank fraud detection?", open=False):
|
| 630 |
+
gr.Markdown(
|
| 631 |
+
"""
|
| 632 |
+
Bank fraud detection is the process of identifying fraudulent activities or transactions
|
| 633 |
+
that may pose a risk to a bank or its customers. It is essential to detect fraudulent
|
| 634 |
+
activities to prevent financial losses and protect the integrity of the banking system.
|
| 635 |
+
"""
|
| 636 |
+
)
|
| 637 |
+
|
| 638 |
+
with gr.Accordion("Why is it important to protect this data?", open=False):
|
| 639 |
+
gr.Markdown(
|
| 640 |
+
"""
|
| 641 |
+
Banking and financial data often contain sensitive personal information, such as income,
|
| 642 |
+
spending habits, and account numbers. Protecting this information ensures that customers'
|
| 643 |
+
privacy is respected and safeguarded from unauthorized access.
|
| 644 |
+
"""
|
| 645 |
+
)
|
| 646 |
+
|
| 647 |
+
with gr.Accordion("Why is Fully Homomorphic Encryption (FHE) a good solution?", open=False):
|
| 648 |
+
gr.Markdown(
|
| 649 |
+
"""
|
| 650 |
+
Fully Homomorphic Encryption (FHE) is a powerful technique for enhancing privacy and accuracy
|
| 651 |
+
in the context of fraud detection, particularly when dealing with sensitive banking data. FHE
|
| 652 |
+
allows for the encryption of data, which can then be processed and analyzed without ever needing
|
| 653 |
+
to decrypt it.
|
| 654 |
+
Each party involved in the detection process can collaborate without compromising user privacy,
|
| 655 |
+
minimizing the risk of data leaks or breaches. The data remains confidential throughout the entire
|
| 656 |
+
process, ensuring that the privacy of users is maintained.
|
| 657 |
+
"""
|
| 658 |
+
)
|
| 659 |
+
|
| 660 |
+
gr.Markdown(
|
| 661 |
+
"""
|
| 662 |
+
<p style="text-align: center;">
|
| 663 |
+
Below, we will explain the flow in the image by simulating a purchase you've just made, and show you how our fraud detection model processes the transaction.
|
| 664 |
+
</p>
|
| 665 |
+
"""
|
| 666 |
+
)
|
| 667 |
+
|
| 668 |
+
|
| 669 |
gr.Markdown(
|
| 670 |
f"""
|
| 671 |
<p align="center">
|
|
|
|
| 675 |
)
|
| 676 |
|
| 677 |
|
| 678 |
+
|
| 679 |
+
|
| 680 |
+
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
|
| 684 |
+
|
| 685 |
+
|
| 686 |
+
|
| 687 |
+
|
| 688 |
+
|
| 689 |
+
|
| 690 |
+
|
| 691 |
+
|
| 692 |
+
|
| 693 |
+
|
| 694 |
+
|
| 695 |
+
|
| 696 |
+
|
| 697 |
+
|
| 698 |
+
|
| 699 |
+
|
| 700 |
+
|
| 701 |
+
|
| 702 |
+
|
| 703 |
########################## Key Gen Part ##########################
|
| 704 |
|
| 705 |
gr.Markdown(
|
|
|
|
| 976 |
# # </p>
|
| 977 |
# # """
|
| 978 |
# # )
|
| 979 |
+
|
| 980 |
+
|
| 981 |
+
|
| 982 |
+
|
| 983 |
+
|
| 984 |
+
|
| 985 |
+
|
| 986 |
+
|
| 987 |
+
|
| 988 |
+
|
| 989 |
+
|
| 990 |
+
|
| 991 |
+
|
| 992 |
+
|
| 993 |
# with gr.Row():
|
| 994 |
# with gr.Column(elem_id="center_column"):
|
| 995 |
# gr.Image("Img/schema.png", width=200, show_label=False)
|