X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection
The surge of highly realistic synthetic videos produced by contemporary generative systems has significantly increased the risk of malicious use, challenging both humans and existing detectors. Against this backdrop, we take a generator-side view and observe that internal cross-attention mechanisms in these models encode fine-grained speech-motion alignment, offering useful correspondence cues for forgery detection. Building on this insight, we propose X-AVDT, a robust and generalizable deepfake
Record details
Published: 9 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Misinformation
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Echoes: A semantically-aligned music deepfake detection dataset
arXiv · 24 March 2026
SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment
arXiv · 26 March 2026
PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization
arXiv · 31 March 2026
Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard
arXiv · 7 June 2026
Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models
arXiv · 7 June 2026
Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering
arXiv · 15 June 2026
How to cite this record
ethics.ai (9 March 2026), “X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection,” evidence record 7481, https://ethics.ai/record/7481 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.