ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks

Authors: Renshuai Tao, Manyi Le, Chuangchuang Tan, Huan Liu, Haotong Qin, Yao Zhao

Published: 2024-10-24 12:32:22+00:00

AI Summary

The paper introduces ODDN, a novel deepfake detection network addressing the scarcity of paired data in open-world scenarios on online social networks. ODDN uses open-world data aggregation (ODA) and compression-discard gradient correction (CGC) to effectively leverage both paired and unpaired data, improving robustness against compression variations.

Abstract

Despite significant advances in deepfake detection, handling varying image quality, especially due to different compressions on online social networks (OSNs), remains challenging. Current methods succeed by leveraging correlations between paired images, whether raw or compressed. However, in open-world scenarios, paired data is scarce, with compressed images readily available but corresponding raw versions difficult to obtain. This imbalance, where unpaired data vastly outnumbers paired data, often leads to reduced detection performance, as existing methods struggle without corresponding raw images. To overcome this issue, we propose a novel approach named the open-world deepfake detection network (ODDN), which comprises two core modules: open-world data aggregation (ODA) and compression-discard gradient correction (CGC). ODA effectively aggregates correlations between compressed and raw samples through both fine-grained and coarse-grained analyses for paired and unpaired data, respectively. CGC incorporates a compression-discard gradient correction to further enhance performance across diverse compression methods in OSN. This technique optimizes the training gradient to ensure the model remains insensitive to compression variations. Extensive experiments conducted on 17 popular deepfake datasets demonstrate the superiority of the ODDN over SOTA baselines.