A contrastive-learning and LLM-based multimodal model reports 88.9% accuracy on Fakeddit, slightly ahead of smaller baselines but with an unclear role for the contrastive component.
Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
AI-synthesized faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social impacts. Although progress has been made in developing automatic methods to detect AI-synthesized faces, there is no open platform to study the human performance of AI-synthesized faces detection. In this work, we develop an online platform called Open-eye to study the human performance of AI-synthesized face detection. We describe the design and workflow of the Open-eye in this paper.
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Self-Learning Multimodal Approach for Fake News Detection
A contrastive-learning and LLM-based multimodal model reports 88.9% accuracy on Fakeddit, slightly ahead of smaller baselines but with an unclear role for the contrastive component.