Abstract: To address the degradation of fine-grained forgery traces, high-frequency information, and boundary artifacts caused by platform transcoding, H.264 compression, JPEG compression, and other forms of degradation during network transmission, which may further lead to local discriminative attention drift, global representation shift, and insufficient cross-quality generalization in deepfake detection models, a Compression-Paired Hyperspherical Consistency (CPHC) learning framework is proposed. Instead of simply treating samples with different compression qualities as ordinary data augmentation and mixing them during training, CPHC organizes the Raw, C23, and C40 versions of the same face frame into source-aligned multi-quality views and explicitly exploits the cross-quality correspondences along the compression degradation chain to learn stable forgery-discriminative representations. At the local spatial-response level, a Local Compressed Attention Consistency (LCAC) module is constructed to characterize discriminative regions under different compression views based on Class Activation Maps (CAMs). Pairwise CAM alignment between adjacent quality views and a shared CAM reference across the three views are employed to guide low-quality views to preserve stable local discriminative evidence, thereby suppressing interference from background noise, compression block artifacts, and irrelevant regions. At the global representation level, a Global Hyperspherical Consistency Constraint (GHCC) is designed to normalize image features onto a unit hypersphere. The von Mises–Fisher (vMF) distribution is further employed to constrain the consistency of class centers and feature distributions for the same real/fake label across different compression qualities, thereby alleviating global class-structure shifts caused by compression degradation. Experimental results show that CPHC achieves an average ACC of 87.02%±0.34% and an average AUC of 91.30%±0.32% on the C40 strongly compressed test set of FaceForensics++, outperforming the baseline by 4.50 and 5.69 percentage points, respectively, and achieving a higher average AUC than seven mainstream methods. Further evaluations under unseen JPEG75, JPEG50, and JPEG25 compression conditions, as well as on the cross-dataset CDF-v2, DFDC, and DeeperForensics benchmarks, demonstrate favorable generalization performance. In the cross-domain evaluation of diffusion-generated forgeries, with FF++ as the source domain and DiFF as the target domain, CPHC achieves an average AUC of 83.13% across four subsets. Ablation studies further show that LCAC and GHCC play complementary roles in stabilizing local discriminative regions and maintaining global class-structure consistency, respectively, and their joint use further improves detection performance under strong compression. These results demonstrate that CPHC effectively mitigates local response drift and global representation shift caused by compression degradation while maintaining stable detection and generalization performance under strong compression, unseen compression, and cross-domain scenarios.

摘要： 针对深度伪造图像在网络传播过程中易受到平台转码、H.264压缩和JPEG压缩等退化影响，导致细粒度伪造痕迹、高频信息及边界伪影被削弱，进而造成局部判别关注漂移、全局表征偏移和跨质量泛化能力下降的问题，提出压缩配对超球面一致性学习框架(Compression-Paired Hyperspherical Consistency，CPHC)。不同于将不同压缩质量样本作为普通数据增强进行简单混合，CPHC将同一人脸帧在Raw、C23和C40三种压缩质量下的版本组织为同源多质量视图，显式利用压缩退化链中的跨质量对应关系学习稳定的伪造判别表征。在局部空间响应层面，构建局部压缩注意力一致性模块(LCAC)，基于类别激活图刻画不同压缩视图下的判别关注区域，并通过相邻质量视图的成对CAM对齐与三视图共享CAM参考，引导低质量视图保持稳定的局部判别证据，抑制背景噪声、压缩块效应和无关区域的干扰。在全局表征层面，设计全局超球面一致性约束(GHCC)，将图像特征归一化到单位超球面空间，并利用von Mises–Fisher(vMF)分布约束同一真假标签在不同压缩质量下的类别中心和特征分布一致性，从而缓解压缩退化造成的全局类别结构偏移。实验结果表明，CPHC在FaceForensics++的C40强压缩测试集上取得87.02%±0.34%的平均ACC和91.30%±0.32%的平均AUC，较Baseline分别提高4.50和5.69个百分点，并取得优于7种主流方法的平均AUC。进一步在JPEG75、JPEG50和JPEG25未知压缩条件，以及CDF-v2、DFDC和DeeperForensics跨数据集场景下测试，CPHC均表现出较好的泛化性能；在以FF++为源域、DiFF为目标域的扩散生成伪造跨域实验中，四个子集的平均AUC达到83.13%。消融实验表明，LCAC和GHCC分别从局部判别区域稳定性与全局类别结构一致性两个层面发挥互补作用，二者联合能够进一步提升强压缩条件下的检测性能。上述结果说明，CPHC能够有效缓解压缩退化引起的局部响应漂移与全局表征偏移，并在强压缩、未知压缩及跨域场景下保持较稳定的检测与泛化能力。