LLMs Are Not Yet Ready for Deepfake Image Detection

• URL: http://arxiv.org/abs/2506.10474v1
• Date: Thu, 12 Jun 2025 08:27:24 GMT
• Title: LLMs Are Not Yet Ready for Deepfake Image Detection
• Authors: Shahroz Tariq, David Nguyen, M. A. P. Chamikara, Tingmin Wu, Alsharif Abuadbba, Kristen Moore,
• Abstract summary: Vision-language models (VLMs) have emerged as promising tools across various domains.<n>This study focuses on three primary deepfake types: faceswap, reenactment, and synthetic generation.<n>Our analysis indicates that while VLMs can produce coherent explanations and detect surface-level anomalies, they are not yet dependable as standalone detection systems.
• Score: 8.364956401923108
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing sophistication of deepfakes presents substantial challenges to the integrity of media and the preservation of public trust. Concurrently, vision-language models (VLMs), large language models enhanced with visual reasoning capabilities, have emerged as promising tools across various domains, sparking interest in their applicability to deepfake detection. This study conducts a structured zero-shot evaluation of four prominent VLMs: ChatGPT, Claude, Gemini, and Grok, focusing on three primary deepfake types: faceswap, reenactment, and synthetic generation. Leveraging a meticulously assembled benchmark comprising authentic and manipulated images from diverse sources, we evaluate each model's classification accuracy and reasoning depth. Our analysis indicates that while VLMs can produce coherent explanations and detect surface-level anomalies, they are not yet dependable as standalone detection systems. We highlight critical failure modes, such as an overemphasis on stylistic elements and vulnerability to misleading visual patterns like vintage aesthetics. Nevertheless, VLMs exhibit strengths in interpretability and contextual analysis, suggesting their potential to augment human expertise in forensic workflows. These insights imply that although general-purpose models currently lack the reliability needed for autonomous deepfake detection, they hold promise as integral components in hybrid or human-in-the-loop detection frameworks.

Related papers

• FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes [9.462613446025001]
  Face-fake Deepfake videos pose growing risks to digital security, privacy, and media integrity.<n>FAME is a framework designed to capture subtle artifacts specific to different face-generative models.<n>Results show that FAME consistently outperforms existing methods in both accuracy and runtime.
  arXiv  Detail & Related papers  (2025-06-13T05:47:09Z)
• Transferable Adversarial Attacks on Black-Box Vision-Language Models [63.22532779621001]
  adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts.<n>We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information.<n>We discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations.
  arXiv  Detail & Related papers  (2025-05-02T06:51:11Z)
• Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward [1.7971686967440696]
  V$2$R-Bench is a benchmark framework for evaluating Visual Variation Robustness of LVLMs.<n>We show that advanced models that excel at complex vision-language tasks significantly underperform on simple tasks such as object recognition.<n>These vulnerabilities stem from error accumulation in the pipeline architecture and inadequate multimodal alignment.
  arXiv  Detail & Related papers  (2025-04-23T14:01:32Z)
• Can Multi-modal (reasoning) LLMs work as deepfake detectors? [6.36797761822772]
  We benchmark 12 latest multi-modal LLMs against traditional deepfake detection methods across multiple datasets.<n>Our findings indicate that best multi-modal LLMs achieve competitive performance with promising generalization ability with zero shot.<n>This study highlights the potential of integrating multi-modal reasoning in future deepfake detection frameworks.
  arXiv  Detail & Related papers  (2025-03-25T21:47:29Z)
• TruthLens:A Training-Free Paradigm for DeepFake Detection [4.64982780843177]
  We introduce TruthLens, a training-free framework that reimagines deepfake detection as a visual question-answering (VQA) task.<n>TruthLens utilizes state-of-the-art large vision-language models (LVLMs) to observe and describe visual artifacts.<n>By adopting a multimodal approach, TruthLens seamlessly integrates visual and semantic reasoning to not only classify images as real or fake but also provide interpretable explanations.
  arXiv  Detail & Related papers  (2025-03-19T15:41:32Z)
• Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection [18.125287697902813]
  Current Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data.<n>We present a novel framework that unlocks LVLMs' potential capabilities for deepfake detection.
  arXiv  Detail & Related papers  (2025-03-19T03:20:03Z)
• Breaking Focus: Contextual Distraction Curse in Large Language Models [68.4534308805202]
  We investigate a critical vulnerability in Large Language Models (LLMs)<n>This phenomenon arises when models fail to maintain consistent performance on questions modified with semantically coherent but irrelevant context.<n>We propose an efficient tree-based search methodology to automatically generate CDV examples.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)

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.