Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

...

...

...

...

...

...

...

...

...

Excerpt
namesummary

🔒 Data leakage prevention is crucial in today's digital age! It's all about safeguarding sensitive information from unauthorized access or accidental disclosure. At Unique, we take this responsibility seriously. With our cutting-edge technology and robust security measures, we are dedicated to preventing data leaks and ensuring your valuable data remains confidential and protected.

...

Table of Contents
minLevel1
maxLevel6
outlinefalse
styledefault
typelist
printabletrue

...

Drawio
mVer2
zoom1
simple0
inComment0
custContentId566724339
pageId500105333
lbox1
diagramDisplayNameUntitled Diagram-1716730316435.drawio
contentVer2
revision2
baseUrlhttps://unique-ch.atlassian.net/wiki
diagramNameUntitled Diagram-1716730316435.drawio
pCenter0
width1905.0000000000002
links
tbstyle
height912.0000000000001

Methods

I DLP Proxy

Panel
panelIconId1f4e4
panelIcon:outbox_tray:
panelIconText📤
bgColor#F4F5F7

This form of DLP is not implemented by Unique. Unique and its platform profit from the clients existing infrastructure that prevents leakages as it does for any other site like googling it or pasting by accident into a text field.

...

Depending on the proxy and DLPs speed, this method can have a latency, speed, and User Experience impact which Unique cannot can sadly not mitigate as they are fully dependent on the clients' system throughput.

II Analytics APIs

Panel
panelIconId2139
panelIcon:information_source:
panelIconTextℹ️
bgColor#DEEBFF

Main article: Analytics

This is more of a post-processing, controlling sort of prevention driven by some of our key clients. While actively monitoring user input and trying to avoid leakages, some cases can only be really detected when scanning and post-processing the prompts, messages, and chats.

...

This approach does not affect the end users in either latency or speed as it is completely asynchronous.

Log Fields Configuration

Each entry logged by the Unique API will contain the following mandatory fields:

  • timestamp: The date and time of the query, formatted as DD-MM-YYYY; HH:MM:SS GMT+X.

  • username: The identifier of the user who initiated the query.

  • prompt: The user's query to Unique, excluding any sensitive prompt engineering sections.

Example Log Entry

Code Block
{
 "timestamp": "01-01-2024; 14:23:05 GMT+1",
 "username": "mheppler",
 "prompt": "Give me the list of all employees within Unique."
}

DLP Policy Configuration

To ensure compliance with privacy laws and regulations, the following considerations must be taken into account when configuring DLP policies:

  • Privacy Compliance: Ensure that monitoring practices are compliant with GDPR, CCPA, and other applicable regulations.

  • Encryption Handling: Configure SSL interception to inspect encrypted traffic while managing trust certificates responsibly.

  • Policy Definition: Clearly define what constitutes sensitive data and the conditions under which it is monitored and blocked.

  • Ethical Transparency: Maintain transparent communication with users regarding the extent and purpose of monitoring.

Scan/Extract Frequency

The API is configured to allow paginated daily scans of log files, aligning with the operational practices of Security Operations Center (SOC) teams. This frequency supports efficient management and timely response to potential data leakage incidents.

Review by Clients Compliance teams

Output / findings of DLP scans should be regularly reviewed (regular sample checks) by the respective client’s compliance and/or data protection team. It is not the responsibility of Unique to check output (not allowed by contractual terms and also not part of the Unique service offering). Clients should make sure that the output/ findings are handled according to internal guidelines, policies and regulations.

Reporting issues

Please report if you experience any issues to enterprise-support@unique.ch

III Pre-LLM DLP Calling

Panel
panelIconId1f6a7
panelIcon:construction:
panelIconText🚧
bgColor#FFFAE6

This feature does not exist and would need to be offered and built.

Scenarios

Scenario

Handled with method

Data/File Upload Scans

Proxy

Usually the existing DLP solutions of the client scan the uploaded files during web browsing activities, the DLP's role is primarily at the proxy level. Here, the DLP system inspects web traffic to identify any potential transmission of sensitive data.

Prompts

Proxy and Analytics API

Unique offers an API that can be integrated with the existing DLP systems to monitor the data being processed. The API is designed to work with the bank's existing security infrastructure to log queries and extract them for DLP inspection.

There is no real-time interception by DLP systems as the response time to receive answers to prompts (questions) would be too long for chat interactions (incl. streaming). Instead, the DLP system will scan the prompts during post-chat analysis. This approach allows for a balance between user experience and security, ensuring that sensitive information is not inadvertently exposed during interactions.

...