Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913044491141120 |
|---|---|
| author | Fu, Rong Wang, Ziming Meng, Chunlei Lu, Jiaxuan Wu, Jiekai Qian, Kangan Zhang, Hao Fong, Simon |
| author_facet | Fu, Rong Wang, Ziming Meng, Chunlei Lu, Jiaxuan Wu, Jiekai Qian, Kangan Zhang, Hao Fong, Simon |
| contents | As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a unified framework for revocable multimodal sentiment analysis that combines structured representation learning with a certifiable parameter-modification pipeline. Revocability is critical in privacy-sensitive applications where users or regulators may request removal of modality-specific information. MBD learns property-aware embeddings and employs generator-based reconstruction to recover missing channels while preserving task-relevant signals. For deletion requests, the framework applies saliency-driven candidate selection and a calibrated Gaussian update to produce a machine-verifiable Modality Deletion Certificate. Experiments on benchmark datasets show that MBD achieves strong predictive performance under incomplete inputs and delivers a practical privacy-utility trade-off, positioning surgical unlearning as an efficient alternative to full retraining. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16144 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis Fu, Rong Wang, Ziming Meng, Chunlei Lu, Jiaxuan Wu, Jiekai Qian, Kangan Zhang, Hao Fong, Simon Computation and Language Machine Learning As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a unified framework for revocable multimodal sentiment analysis that combines structured representation learning with a certifiable parameter-modification pipeline. Revocability is critical in privacy-sensitive applications where users or regulators may request removal of modality-specific information. MBD learns property-aware embeddings and employs generator-based reconstruction to recover missing channels while preserving task-relevant signals. For deletion requests, the framework applies saliency-driven candidate selection and a calibrated Gaussian update to produce a machine-verifiable Modality Deletion Certificate. Experiments on benchmark datasets show that MBD achieves strong predictive performance under incomplete inputs and delivers a practical privacy-utility trade-off, positioning surgical unlearning as an efficient alternative to full retraining. |
| title | Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2602.16144 |