多模态行为传感器用于谎言检测:整合视觉,听觉和生成推理线索
Daniel Grabowski1, Kamila Łuczaj1, Khalid Saeed1,2
1Faculty of Computer Science, Białystok University of Technology, 15-351 Białystok, Poland.
Sensors (Basel, Switzerland)
|October 16, 2025
概括
本研究介绍了使用多式联络数据进行谎言检测的AI框架. 它结合了视频,音频和语言模型,以准确地识别欺骗与可解释推理.
科学领域:
- 人工智能的人工智能
- 行为科学 行为科学
- 计算语言学 计算语言学
背景情况:
- 多模式AI的进步使得新的传感器启发的谎言检测成为可能.
- 整合行为感知与生成推理是关键.
研究的目的:
- 通过使用深度视频/音频处理和大型语言模型,展示一个欺骗检测框架.
- 通过连锁思维 (CoT) 提示和提示级融合,使可解释的欺骗假设产生.
主要方法:
- 利用ViViT和HuBERT作为数字行为传感器来提取情绪和认知线索.
- 采用GPT-5进行提示级融合,对视频,语言和情感进行对齐,以实现零射击推断.
- 在DOLOS数据集上处理视觉,转录和情绪识别输出.
主要成果:
- 多模式融合和CoT推理显著提高了欺骗分类的准确性.
- 该系统证明了可解释的欺骗假设生成,而无需对特定任务进行微调.
- 持续学习设置显示了情感理解的有效转移到欺骗分类.
结论:
- 拟议的AI框架有效地将原始行为数据和谎言检测的语义推理结合起来.
- 这种方法奠定了人工智能驱动的欺骗检测与可解释的传感器类型的基础.
- 以传感器为灵感的AI为理解和检测欺骗行为提供了一个有希望的方向.
相关概念视频
Understanding Deception
151
Deception is a pervasive aspect of human communication. Empirical studies have shown that most individuals engage in some form of deceit on a daily basis, with approximately 20% of social exchanges involving deceptive elements. Lying follows a developmental trajectory, peaking during adolescence and declining with age, possibly due to the maturation of cognitive control and social accountability.Cognitive and Social Factors in Deception DetectionDespite its prevalence, accurately detecting...
151
Non-Verbal Cues
275
Non-verbal communication extends beyond gestures and facial expressions to include vocal elements known as paralanguage. Paralanguage consists of non-verbal vocal cues such as pitch, loudness, speech rate, pauses, and non-verbal vocalizations like laughter, sighs, and moans. These elements not only accompany speech but also provide critical emotional and contextual information.The Role of Paralanguage in CommunicationParalanguage adds depth to spoken language by conveying emotions and...
275


