Trustworthy Deepfake Defense for Consumer Applications via Frequency-Preserving Resizing and Dual-Branch Forensics

Deepfakes pose a growing threat to consumer security and trust, enabling identity theft, financial fraud, and misinformation across social and mobile platforms. Reliable detection pipelines are essential for trustworthy consumer applications, yet many current systems rely on conventional resizing operators, such as bilinear and bicubic interpolation, that behave as low-pass filters andsystematically attenuatemanipulation-relevant high-frequency (HF) forensic cues during preprocessing, a problem that learned rescaling methods optimized for perceptual quality have not addressed. To close this gap, we propose a proactive twostage forensic defense framework. The first stage, the Frequency-Aware Information Preserving Network (FA-IPNet), is the first rescaling module designed with an explicitforensicobjective, retaining manipulation-sensitive HF cues rather than maximizing perceptual reconstruction quality, at only 0.304K parameters and 2.91M FLOPs. FA-IPNet introduces a task-oriented diagnostic to quantify directional forensic-signal attenuation and addresses it through fixed Haar decomposition, multi-spectral channel attention withbounded affine recalibration, and attention-aware channel reduction. The second stage, the Adaptive Frequency-Enhanced Forgery Detection Network (AFE-FDNet), is a dual-branch detector whose spatial branch employs retentive vision transformers withdistance-decayed dual-axis attentionand head-specific log-decay masks, and whose frequency branch applies learnablemulti-scale spectral band decompositionwith per-band windowed attention enhancement and temperature-scaled pyramid cross-band aggregation. Evaluations on FaceForensics++, Celeb-DF-V2, DFDC, and the diffusion-based DF40 dataset demonstrate that FA-IPNet better preserves forensic signals than interpolation-based resizing, and that AFE-FDNet achieves robust generalization including on diffusion-era forgeries under a zero-shot protocol. Together, they establish a robust and trustworthy defense for consumer-facing applications against deepfake-driven security and privacy risks.