针对伪造人脸检测中数据不平衡问题，提出动态损失重加权方法。
Robust AI-Generated Face Detection with Imbalanced Data
- 采用动态损失重加权与排序优化结合的框架
- 在严重不平衡数据下仍保持高检测准确率
- 适合应对新型生成模型带来的分布偏移
深度伪造技术借助变分自编码器和生成对抗网络等先进AI方法，已从研究娱乐演变为恶意工具，严重威胁数字可信度。当前检测方法从基于CNN的局部伪影分析，发展到使用视觉变换器和多模态模型（如CLIP）捕捉全局异常，提升跨域泛化能力。尽管取得进展，现有顶尖检测器在应对新兴生成模型引起的分布偏移，以及真实与伪造样本间严重类别不平衡方面仍面临挑战，限制了鲁棒性和准确性。为此，本文提出一种融合动态损失重加权与排序优化的框架，在不平衡数据条件下实现更优泛化性能与检测效果。代码已公开于https://github.com/Purdue-M2/SP_CUP。
原文摘要 · Abstract (English)
Deepfakes, created using advanced AI techniques such as Variational Autoencoder and Generative Adversarial Networks, have evolved from research and entertainment applications into tools for malicious activities, posing significant threats to digital trust. Current deepfake detection techniques have evolved from CNN-based methods focused on local artifacts to more advanced approaches using vision transformers and multimodal models like CLIP, which capture global anomalies and improve cross-domain generalization. Despite recent progress, state-of-the-art deepfake detectors still face major challenges in handling distribution shifts from emerging generative models and addressing severe class imbalance between authentic and fake samples in deepfake datasets, which limits their robustness and detection accuracy. To address these challenges, we propose a framework that combines dynamic loss reweighting and ranking-based optimization, which achieves superior generalization and performance under imbalanced dataset conditions. The code is available at https://github.com/Purdue-M2/SP_CUP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。