Skip to main content
Search
Menu

Anonymization Defense GUARD

Anonymization Defense GUARD ([GU]arding [A]nonymization p[R]oce[D]ures) aims to investigate and address vulnerabilities in the use of facial manipulation-based anonymization methods.

The automotive industry, like many other industries, relies heavily on data-hungry AI systems, such as object detection, for achieving their goal. However, acquiring sufficient data for these systems raises concerns about privacy and data integrity.

Consequently, the industry is exploring methods for directly anonymizing data and removing identity information while preserving attribute information. Research and services already exist to tackle this challenge. 

Guard aims to investigate vulnerabilities in using facial manipulation-based anonymization methods such as FaceDancer (Rosberg, 2023). There is evidence that malicious  actors can train adversarial AI models to reconstruct the original identity, in the event of adversarial attacks, causing the anonymization model to fail. In the context of cyber-security, we emphasize the need for identifying necessary defense measures against various types of attacks, such as reconstruction or adversarial attacks. 

The GUARD project builds on the results and findings from the MIDAS project.

Summary

Project name

GUARD

Status

Active

Region

Västra Götaland Region

RISE role in project

Project management, Research

Project start

Duration

Two years

Total budget

Just over 7,5 million SEK

Partner

Engage Studios AB, Halmstad University

Funders

Vinnova, Avancerad Digitalisering

Project members

Tor Skoglund

Contact person

Tor Skoglund

+46 72 215 58 42

Read more about Tor

Contact Tor
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

* Mandatory By submitting the form, RISE will process your personal data.