SVC 2025: the First Multimodal Deception Detection Challenge

TL;DR

The SVC 2025 challenge introduces a benchmark for cross-domain multimodal deception detection, encouraging models that generalize across diverse datasets using audio, video, and text cues to improve real-world deception detection systems.

Contribution

This paper presents the first multimodal deception detection challenge focusing on cross-domain generalization across heterogeneous datasets.

Findings

21 teams participated in the challenge

Models demonstrated varying degrees of cross-domain generalization

Benchmark fosters development of more adaptable deception detection systems

Abstract

Deception detection is a critical task in real-world applications such as security screening, fraud prevention, and credibility assessment. While deep learning methods have shown promise in surpassing human-level performance, their effectiveness often depends on the availability of high-quality and diverse deception samples. Existing research predominantly focuses on single-domain scenarios, overlooking the significant performance degradation caused by domain shifts. To address this gap, we present the SVC 2025 Multimodal Deception Detection Challenge, a new benchmark designed to evaluate cross-domain generalization in audio-visual deception detection. Participants are required to develop models that not only perform well within individual domains but also generalize across multiple heterogeneous datasets. By leveraging multimodal data, including audio, video, and text, this challenge encourages the design of models capable of capturing subtle and implicit deceptive cues. Through this benchmark, we aim to foster the development of more adaptable, explainable, and practically deployable deception detection systems, advancing the broader field of multimodal learning. By the conclusion of the workshop competition, a total of 21 teams had submitted their final results. https://sites.google.com/view/svc-mm25 for more information.