# Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge

arXiv: https://arxiv.org/abs/2604.28022 · HTML: https://mlsanity.com/paper/2604.28022/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection](https://mlsanity.com/paper/2201.07131/) (2022)
- [Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization](https://mlsanity.com/paper/2005.14405/) (2020)
- [Spatiotemporal Inconsistency Learning for DeepFake Video Detection](https://mlsanity.com/paper/2109.01860/) (2021)
- [Self-Supervised Video Forensics by Audio-Visual Anomaly Detection](https://mlsanity.com/paper/2301.01767/) (2023)
- [Voice-Face Homogeneity Tells Deepfake](https://mlsanity.com/paper/2203.02195/) (2022)
- [Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization](https://mlsanity.com/paper/2305.01979/) (2023)
- [Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors](https://mlsanity.com/paper/2109.02993/) (2021)
- [Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection](https://mlsanity.com/paper/2401.05746/) (2024)
- [Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies](https://mlsanity.com/paper/2408.06753/) (2024)
- [Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges](https://mlsanity.com/paper/2406.06965/) (2024)
- [BIAS: A Body-based Interpretable Active Speaker Approach](https://mlsanity.com/paper/2412.05150/) (2024)
- [ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection](https://mlsanity.com/paper/2412.08594/) (2024)
- [Statistics-aware Audio-visual Deepfake Detector](https://mlsanity.com/paper/2407.11650/) (2024)
- [FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units](https://mlsanity.com/paper/2505.08294/) (2025)

## Abstract (arXiv)

Current DeepFake detection scenarios are mostly binary, yet data manipulation can vary across audio, video, or both, whose variability is not captured in binary settings. Four-class audio-visual formulations address this by discriminating manipulation type, but introduce an unresolved problem: models may rely solely on data source integrity to detect DeepFakes without evaluating their semantic consistency. If the DeepFake origin is not in the data source but in its content, can semantic mismatch be assessed by the state-of-the-art? This paper proposes a new evaluation setup, extending the four-class formulation by explicitly modeling semantic-level inconsistency between authentic modalities with the introduction of a new class: Real Audio-Real Video with Semantic Mismatch RARV-SMM. We assess the robustness of state-of-the-art models in this new realistic DeepFake setting, using the FakeAVCeleb dataset, highlighting the limitations of existing approaches when faced with semantic mismatch data. We further introduce three RARV-SMM variants that expose distinct architectural vulnerabilities as audio-visual divergence increases. We also propose a semantic reinforcement strategy that incorporates the semantic mismatch class and ImageBind embeddings to probe whether an explicit semantic coherence signal improves detection across architectures with different detection strategies, on FakeAVCeleb and LAV-DF, contributing toward more realistic DeepFake detectors. The source code available at https://github.com/sharayu-20/deepfake-semantic-mismatch.