Best Paper Award for Sandra Bergmann at IWBF 2023 in Barcelona

Symbolic picture for the article. The link opens the image in a large view.

Sandra Bergmann, Denise Moussa, Fabian Brand, André Kaup and Christian Riess received the Best Paper Award for their article titled “Frequency-Domain Analysis of Traces for the Detection of AI-based Compression” at the international workshop IWBF 2023. The paper presents the first systematic forensic analysis of AI-compressed images as JPEG is replaced by JPEG AI in 2024. AI compression leaves traces in the frequency domain, which can be used to detect AI compressed images. To further understand these traces, Bergmann et al. have performed various experiments on the detectability, robustness, and repeated compression of the artifacts in the frequency domain. The work has been presented in Barcelona, Spain and can be found here.