Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.15867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908515933618176 |
|---|---|
| author | Kundu, Rohit Jia, Shan Mohanty, Vishal Balachandran, Athula Roy-Chowdhury, Amit K. |
| author_facet | Kundu, Rohit Jia, Shan Mohanty, Vishal Balachandran, Athula Roy-Chowdhury, Amit K. |
| contents | Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary classification (real vs. fake) and lack interpretability. To address these challenges, we propose TruthLens, a novel, unified, and highly generalizable framework that goes beyond traditional binary classification, providing detailed, textual reasoning for its predictions. Distinct from conventional methods, TruthLens performs MLLM grounding.
TruthLens uses a task-driven representation integration strategy that unites global semantic context from a multimodal large language model (MLLM) with region-specific forensic cues through explicit cross-modal adaptation of a vision-only model. This enables nuanced, region-grounded reasoning for both face-manipulated and fully synthetic content, and supports fine-grained queries such as "Does the eyes/nose/mouth look real or fake?"- capabilities beyond pretrained MLLMs alone. Extensive experiments across diverse datasets demonstrate that TruthLens sets a new benchmark in both forensic interpretability and detection accuracy, generalizing to seen and unseen manipulations alike. By unifying high-level scene understanding with fine-grained region grounding, TruthLens delivers transparent DeepFake forensics, bridging a critical gap in the literature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15867 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TruthLens: Visual Grounding for Universal DeepFake Reasoning Kundu, Rohit Jia, Shan Mohanty, Vishal Balachandran, Athula Roy-Chowdhury, Amit K. Computer Vision and Pattern Recognition Artificial Intelligence Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary classification (real vs. fake) and lack interpretability. To address these challenges, we propose TruthLens, a novel, unified, and highly generalizable framework that goes beyond traditional binary classification, providing detailed, textual reasoning for its predictions. Distinct from conventional methods, TruthLens performs MLLM grounding. TruthLens uses a task-driven representation integration strategy that unites global semantic context from a multimodal large language model (MLLM) with region-specific forensic cues through explicit cross-modal adaptation of a vision-only model. This enables nuanced, region-grounded reasoning for both face-manipulated and fully synthetic content, and supports fine-grained queries such as "Does the eyes/nose/mouth look real or fake?"- capabilities beyond pretrained MLLMs alone. Extensive experiments across diverse datasets demonstrate that TruthLens sets a new benchmark in both forensic interpretability and detection accuracy, generalizing to seen and unseen manipulations alike. By unifying high-level scene understanding with fine-grained region grounding, TruthLens delivers transparent DeepFake forensics, bridging a critical gap in the literature. |
| title | TruthLens: Visual Grounding for Universal DeepFake Reasoning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.15867 |