REVIEW 6 cited by
FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
read the original abstract
The ability to distinguish whether an image is generated by artificial intelligence (AI) is a crucial ingredient in human intelligence, usually accompanied by a complex and dialectical forensic and reasoning process. However, current fake image detection models and databases focus on binary classification without understandable explanations for the general populace. This weakens the credibility of authenticity judgment and may conceal potential model biases. Meanwhile, large multimodal models (LMMs) have exhibited immense visual-text capabilities on various tasks, bringing the potential for explainable fake image detection. Therefore, we pioneer the probe of LMMs for explainable fake image detection by presenting a multimodal database encompassing textual authenticity descriptions, the FakeBench. For construction, we first introduce a fine-grained taxonomy of generative visual forgery concerning human perception, based on which we collect forgery descriptions in human natural language with a human-in-the-loop strategy. FakeBench examines LMMs with four evaluation criteria: detection, reasoning, interpretation and fine-grained forgery analysis, to obtain deeper insights into image authenticity-relevant capabilities. Experiments on various LMMs confirm their merits and demerits in different aspects of fake image detection tasks. This research presents a paradigm shift towards transparency for the fake image detection area and reveals the need for greater emphasis on forensic elements in visual-language research and AI risk control. FakeBench will be available at https://github.com/Yixuan423/FakeBench.
Forward citations
Cited by 6 Pith papers
-
XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection
A million-scale deepfake benchmark with Edit-Check filtering, dual expert/lay explanations, and EntityScore/EvidenceScore shows fine-tuned detectors collapse under generator shift while surface fluency remains.
-
SAGA: Source Attribution of Generative AI Videos
SAGA is a multi-granular source attribution system for generative AI videos that identifies the exact generator with state-of-the-art accuracy using only 0.5% labeled data per class.
-
From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection
A multi-agent forensic system integrates multiple evidence sources and debate to detect AI-generated images, reporting 97.05% accuracy on a 6,000-image benchmark while outperforming traditional classifiers.
-
Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images
Locate-Then-Examine improves AI-generated image detection by localizing suspicious regions first then performing region-aware re-examination, while releasing the TRACE dataset of 20k annotated images.
-
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
-
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.