Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models
This addresses a critical gap in deepfake detection for video content, though it is incremental as it builds on existing VLM capabilities.
The paper tackles the problem of Vision-Language Models (VLMs) overlooking temporal inconsistencies in video deepfakes by proposing Forensic Answer-Questioning (FAQ), a benchmark that formulates temporal deepfake analysis as a multiple-choice task, and shows that models fine-tuned on FAQ-IT achieve advanced performance on detection benchmarks.
Current Vision-Language Models (VLMs) for deepfake detection excel at identifying spatial artifacts but overlook a critical dimension: temporal inconsistencies in video forgeries. Adapting VLMs to reason about these dynamic cues remains a distinct challenge. To bridge this gap, we propose Forensic Answer-Questioning (FAQ), a large-scale benchmark that formulates temporal deepfake analysis as a multiple-choice task. FAQ introduces a three-level hierarchy to progressively evaluate and equip VLMs with forensic capabilities: (1) Facial Perception, testing the ability to identify static visual artifacts; (2) Temporal Deepfake Grounding, requiring the localization of dynamic forgery artifacts across frames; and (3) Forensic Reasoning, challenging models to synthesize evidence for final authenticity verdicts. We evaluate a range of VLMs on FAQ and generate a corresponding instruction-tuning set, FAQ-IT. Extensive experiments show that models fine-tuned on FAQ-IT achieve advanced performance on both in-domain and cross-dataset detection benchmarks. Ablation studies further validate the impact of our key design choices, confirming that FAQ is the driving force behind the temporal reasoning capabilities of these VLMs.