Image Protection Against DeepFakes Using Adversarial Attacks

Design adversarial attacks to protect images against malicious usage of image translation, face manipulation, and other deepfake algorithms.

Required interest(s)

  • Deepfakes
  • Generative Models
  • Human-Centered and Community-Minded Information Systems

What do you get

  • A challenging assignment within a practical environment
  • € 1000 compensation, € 500 + lease car or € 600 + living space
  • Professional guidance
  • Courses aimed at your graduation period
  • Support from our academic Research center at your disposal
  • Two vacation days per month

What you will do

  • 65% Research
  • 10% Analyze, design, realize
  • 25% Documentation

Deepfake technology has gained a lot of attention in the past years, not only due to its fast improvement in such short time span, but especially because of its dangerous potential for malicious applications. Deepfake algorithms –such as image translation– can be used to modify someone’s face or place it in someone else’s body in a realistic way, and make them look like they are saying or doing something they did not.

Thankfully, recent research has started to tackle this problem, by following a seemingly simple yet powerful tactic: using adversarial attacks –through the very same type of network (GAN) used for creating deepfakes– to process images, in a way that renders them unusable for deepfake architectures.

While this approach –also known as deepfake disruption– already shows promising results, it is still in its infancy, and a lot of work is yet to be done. An adversarial attack technique that could generalize against –if not all– existing deepfake methods, would be of great interest to businesses like social media or news sites, where millions of pictures are uploaded every day, in order to protect exposed users and public figures.

About Info Support Research Center

We anticipate on upcoming and future challenges and ensures our engineers develop cutting-edge solutions based on the latest scientific insights. Our research community proactively tackles emerging technologies. We do this in cooperation with renowned scientists, making sure that research teams are positioned and embedded throughout our organisation and our community, so that their insights are directly applied to our business. We truly believe in sharing knowledge, so we want to do this without any restrictions.

Sign up for this assignment

  • Geaccepteerde bestandstypen: docx, doc, txt, pdf.
  • Geaccepteerde bestandstypen: docx, doc, txt, pdf.

Application procedure

  1. 1
  2. Introductory meeting

    Discuss (study) career, interests and ambitions and introduction Info Support.

  1. 2
  2. Review

    Assessment of professional knowledge and personality (capacity, competences and motives).

  1. 3
  2. Selection interview

    Deepen professional knowledge and personality.

  1. 4
  2. The signing of a contract

    Contract offer and invitation for drawing moments.