TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection

• URL: http://arxiv.org/abs/2505.24866v1
• Date: Fri, 30 May 2025 17:59:08 GMT
• Title: TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection
• Authors: Xinqi Xiong, Prakrut Patel, Qingyuan Fan, Amisha Wadhwa, Sarathy Selvam, Xiao Guo, Luchao Qi, Xiaoming Liu, Roni Sengupta,
• Abstract summary: TalkingHeadBench is a benchmark for deepfake talking-head detection.<n>Our dataset includes deepfakes synthesized by leading academic and commercial models.<n>We provide error analysis using Grad-CAM visualizations to expose common failure modes and detectorizable biases.
• Score: 8.166056418369125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of talking-head deepfake generation fueled by advanced generative models has elevated the realism of synthetic videos to a level that poses substantial risks in domains such as media, politics, and finance. However, current benchmarks for deepfake talking-head detection fail to reflect this progress, relying on outdated generators and offering limited insight into model robustness and generalization. We introduce TalkingHeadBench, a comprehensive multi-model multi-generator benchmark and curated dataset designed to evaluate the performance of state-of-the-art detectors on the most advanced generators. Our dataset includes deepfakes synthesized by leading academic and commercial models and features carefully constructed protocols to assess generalization under distribution shifts in identity and generator characteristics. We benchmark a diverse set of existing detection methods, including CNNs, vision transformers, and temporal models, and analyze their robustness and generalization capabilities. In addition, we provide error analysis using Grad-CAM visualizations to expose common failure modes and detector biases. TalkingHeadBench is hosted on https://huggingface.co/datasets/luchaoqi/TalkingHeadBench with open access to all data splits and protocols. Our benchmark aims to accelerate research towards more robust and generalizable detection models in the face of rapidly evolving generative techniques.

Related papers

• Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation [18.402668470092294]
  Synthetic video generation can produce very realistic high-resolution videos that are virtually indistinguishable from real ones.<n>Several video forensic detectors have been recently proposed, but they often exhibit poor generalization.<n>We introduce a novel data augmentation strategy based on the wavelet decomposition and replace specific frequency-related bands to drive the model to exploit more relevant forensic cues.<n>Our method achieves a significant accuracy improvement over state-of-the-art detectors and obtains excellent results even on very recent generative models.
  arXiv  Detail & Related papers  (2025-06-20T07:36:59Z)
• Robust AI-Generated Face Detection with Imbalanced Data [10.360215701635674]
  Current deepfake detection techniques have evolved from CNN-based methods focused on local artifacts to more advanced approaches using vision transformers and multimodal models like CLIP.<n>Despite recent progress, state-of-the-art deepfake detectors still face major challenges in handling distribution shifts from emerging generative models.<n>We propose a framework that combines dynamic loss reweighting and ranking-based optimization, which achieves superior generalization and performance under imbalanced dataset conditions.
  arXiv  Detail & Related papers  (2025-05-04T17:02:10Z)
• AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection [9.540547388707987]
  Ai-GenBench is a novel benchmark designed to address the need for robust detection of AI-generated images in real-world scenarios.<n>By establishing clear evaluation rules and controlled augmentation strategies, Ai-GenBench enables meaningful comparison of detection methods and scalable solutions.
  arXiv  Detail & Related papers  (2025-04-29T15:41:13Z)
• HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection [4.908389661988192]
  HFMF is a comprehensive two-stage deepfake detection framework.<n>It integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism.<n>We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks.
  arXiv  Detail & Related papers  (2025-01-10T00:20:29Z)
• Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model Generalization [6.589206192038365]
  This paper proposes an adversarial meta-learning algorithm using task-specific adaptive sample synthesis and consistency regularization. It boosts both robustness and generalization of the model. Experimental results demonstrate the model's consistent performance across various datasets, outperforming the models in comparison.
  arXiv  Detail & Related papers  (2024-11-12T19:55:07Z)
• Leveraging Mixture of Experts for Improved Speech Deepfake Detection [53.69740463004446]
  Speech deepfakes pose a significant threat to personal security and content authenticity. We introduce a novel approach for enhancing speech deepfake detection performance using a Mixture of Experts architecture.
  arXiv  Detail & Related papers  (2024-09-24T13:24:03Z)
• GM-DF: Generalized Multi-Scenario Deepfake Detection [49.072106087564144]
  Existing face forgery detection usually follows the paradigm of training models in a single domain. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets.
  arXiv  Detail & Related papers  (2024-06-28T17:42:08Z)
• Deepfake Generation and Detection: A Benchmark and Survey [134.19054491600832]
  Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions. This survey comprehensively reviews the latest developments in deepfake generation and detection. We focus on researching four representative deepfake fields: face swapping, face reenactment, talking face generation, and facial attribute editing.
  arXiv  Detail & Related papers  (2024-03-26T17:12:34Z)
• GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning [50.7702397913573]
  The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology. We propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection.
  arXiv  Detail & Related papers  (2024-02-03T03:13:50Z)
• Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions [68.8204255655161]
  Threat detection of weapons and aggressive behavior from live video can be used for rapid detection and prevention of potentially deadly incidents. One way for achieving this is through the use of artificial intelligence and, in particular, machine learning for image analysis. We compare a traditional monolithic end-to-end deep learning model and a previously proposed model based on an ensemble of simpler neural networks detecting fire-weapons via semantic segmentation.
  arXiv  Detail & Related papers  (2020-12-17T15:19:29Z)
• Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference [55.35176938713946]
  We develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its multi-stochastic-layer generative network. We propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a downward generative model. The efficacy and scalability of our models are demonstrated on both unsupervised and supervised learning tasks on big corpora.
  arXiv  Detail & Related papers  (2020-06-15T22:22:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.