Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning
This addresses the problem of practical deepfake detection for security and verification applications, representing a novel method rather than an incremental improvement.
The paper tackles the challenge of deepfake detection in real-world scenarios by introducing HydraFake, a dataset simulating hierarchical generalization testing, and Veritas, a multi-modal large language model-based detector using pattern-aware reasoning. Veritas achieves significant gains across out-of-distribution scenarios compared to previous detectors that fall short on unseen forgeries and data domains.
Deepfake detection remains a formidable challenge due to the complex and evolving nature of fake content in real-world scenarios. However, existing academic benchmarks suffer from severe discrepancies from industrial practice, typically featuring homogeneous training sources and low-quality testing images, which hinder the practical deployments of current detectors. To mitigate this gap, we introduce HydraFake, a dataset that simulates real-world challenges with hierarchical generalization testing. Specifically, HydraFake involves diversified deepfake techniques and in-the-wild forgeries, along with rigorous training and evaluation protocol, covering unseen model architectures, emerging forgery techniques and novel data domains. Building on this resource, we propose Veritas, a multi-modal large language model (MLLM) based deepfake detector. Different from vanilla chain-of-thought (CoT), we introduce pattern-aware reasoning that involves critical reasoning patterns such as "planning" and "self-reflection" to emulate human forensic process. We further propose a two-stage training pipeline to seamlessly internalize such deepfake reasoning capacities into current MLLMs. Experiments on HydraFake dataset reveal that although previous detectors show great generalization on cross-model scenarios, they fall short on unseen forgeries and data domains. Our Veritas achieves significant gains across different OOD scenarios, and is capable of delivering transparent and faithful detection outputs.