DeepFake Mini-Hackathon
The EPFL AI Center and LauzHack is hosting a DeepFake Mini-Hackathon. While rapid advances in GenAI and the increased accessibility to models/compute can lead to impressive advances in science and technology, these tools can be also for malicious purposes, notably deepfake generation. The goal of this hackathon is to leverage the intelligence and creativity of the EPFL community (and surroundings) to better understand and raise awareness about the technology that can be used for deepfake generation and detection.
There will be two tracks:
Generation (red team).
Detection (blue team).
Due to the sensitive nature of this topic, as well as the typical LauzHack rules, there are additional rules that apply for both tracks:
Do not record any deep fakes that are being created during the hackathon (if you have a particular reason why you’d want to do that, speak to the organizers first).
For the Generation (red team) track, please consider the following rules. Our goal is not to limit your creativity - on the contrary, we encourage you to push the boundaries and show us what’s possible! However, it’s important that your well-intended work doesn’t inadvertently cause harm.
As a principle, do not create deep fakes of real people.
For public figures (famous people for which there is a lot of content online), you are allowed to create deep fakes in the confinement of this event - but see rules below.
Every deep fake you create must be very clearly labeled as such.
Refrain from producing deeply offensive content.
No sharing or publishing of generated content or code outside the event without review.
If in doubt: please regularly check-in with organizers to ensure adherence to guidelines.
Tentative schedule
(Fri Sep 13, 6pm): Tutorials/workshops
(Fri Sep 13, 10pm): end of day (can continue working at home)
(Sat Sep 14, 10am): breakfast
(Sat Sep 14, till 3ish): hack, hack, hack
(Sat Sep 14, 4pm): demos
You can form teams of up to 4.