Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.08405 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915930175438848 |
|---|---|
| author | Zhang, Wenli Shi, Xianglong Zhao, Sirui Chen, Xinqi Cheng, Guo Xu, Yifan Xu, Tong Liao, Yong |
| author_facet | Zhang, Wenli Shi, Xianglong Zhao, Sirui Chen, Xinqi Cheng, Guo Xu, Yifan Xu, Tong Liao, Yong |
| contents | Diffusion-based audio-driven talking-head generation enables realistic portrait animation, but also introduces risks of misuse, such as fraud and misinformation. Existing protection methods are largely limited to a single modality, and neither image-only nor audio-only attacks can effectively suppress speech-driven facial dynamics. To address this gap, we propose SyncBreaker, a stage-aware multimodal protection framework that jointly perturbs portrait and audio inputs under modality-specific perceptual constraints. Our key contributions are twofold. First, for the image stream, we introduce nullifying supervision with Multi-Interval Sampling (MIS) across diffusion stages to steer the generation toward the static reference portrait by aggregating guidance from multiple denoising intervals. Second, for the audio stream, we propose Cross-Attention Fooling (CAF), which suppresses interval-specific audio-conditioned cross-attention responses. Both streams are optimized independently and combined at inference time to enable flexible deployment. We evaluate SyncBreaker in a white-box proactive protection setting. Extensive experiments demonstrate that SyncBreaker more effectively degrades lip synchronization and facial dynamics than strong single-modality baselines, while preserving input perceptual quality and remaining robust under purification. Code: https://github.com/kitty384/SyncBreaker. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08405 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation Zhang, Wenli Shi, Xianglong Zhao, Sirui Chen, Xinqi Cheng, Guo Xu, Yifan Xu, Tong Liao, Yong Computer Vision and Pattern Recognition Diffusion-based audio-driven talking-head generation enables realistic portrait animation, but also introduces risks of misuse, such as fraud and misinformation. Existing protection methods are largely limited to a single modality, and neither image-only nor audio-only attacks can effectively suppress speech-driven facial dynamics. To address this gap, we propose SyncBreaker, a stage-aware multimodal protection framework that jointly perturbs portrait and audio inputs under modality-specific perceptual constraints. Our key contributions are twofold. First, for the image stream, we introduce nullifying supervision with Multi-Interval Sampling (MIS) across diffusion stages to steer the generation toward the static reference portrait by aggregating guidance from multiple denoising intervals. Second, for the audio stream, we propose Cross-Attention Fooling (CAF), which suppresses interval-specific audio-conditioned cross-attention responses. Both streams are optimized independently and combined at inference time to enable flexible deployment. We evaluate SyncBreaker in a white-box proactive protection setting. Extensive experiments demonstrate that SyncBreaker more effectively degrades lip synchronization and facial dynamics than strong single-modality baselines, while preserving input perceptual quality and remaining robust under purification. Code: https://github.com/kitty384/SyncBreaker. |
| title | SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08405 |