Can Multi-modal (reasoning) LLMs work as deepfake detectors?
read the original abstract
Deepfake detection remains a critical challenge in the era of advanced generative models, particularly as synthetic media becomes more sophisticated. In this study, we explore the potential of state of the art multi-modal (reasoning) large language models (LLMs) for deepfake image detection such as (OpenAI O1/4o, Gemini thinking Flash 2, Deepseek Janus, Grok 3, llama 3.2, Qwen 2/2.5 VL, Mistral Pixtral, Claude 3.5/3.7 sonnet) . We benchmark 12 latest multi-modal LLMs against traditional deepfake detection methods across multiple datasets, including recently published real-world deepfake imagery. To enhance performance, we employ prompt tuning and conduct an in-depth analysis of the models' reasoning pathways to identify key contributing factors in their decision-making process. Our findings indicate that best multi-modal LLMs achieve competitive performance with promising generalization ability with zero shot, even surpass traditional deepfake detection pipelines in out-of-distribution datasets while the rest of the LLM families performs extremely disappointing with some worse than random guess. Furthermore, we found newer model version and reasoning capabilities does not contribute to performance in such niche tasks of deepfake detection while model size do help in some cases. This study highlights the potential of integrating multi-modal reasoning in future deepfake detection frameworks and provides insights into model interpretability for robustness in real-world scenarios.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
The first public dataset of 10,217 GPT-Image-2 generated images sourced from Twitter in the week after release, with CLIP taxonomy, OCR, face detection, clustering analyses, and a finding that C2PA provenance data is ...
-
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
The first public dataset of 10,217 GPT-image-2 AI-generated images from Twitter, with CLIP taxonomy, OCR, face detection, and clustering analyses, plus the finding that C2PA credentials are stripped by the platform.
-
Noncrossing Duality and the Geometry of Positive Tropical Linear Spaces
A new noncrossing duality in tropical geometry bijectionally links integer points of the positive tropical Grassmannian to noncrossing tableaux and realizes their bounded complexes as subdifferentials of central roof ...
-
Noncrossing Duality and the Geometry of Positive Tropical Linear Spaces
Establishes noncrossing duality linking positive tropical Grassmannian fan structure to noncrossing fans with a bijection to noncrossing tableaux, and realizes bounded complexes of tropical linear spaces as subdiffere...
-
When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents
GPT-Image-2 document forgeries evade human and computational detection while traditional tampering remains detectable, with the model itself failing as a self-judge.
-
A Synthetic Eye Movement Dataset for Script Reading Detection: Real Trajectory Replay on a 3D Simulator
A replay pipeline on a 3D eye simulator generates 144 sessions of synthetic eye movement video that preserves source temporal dynamics for script-reading detection.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.