Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
This addresses privacy and user autonomy in multimodal systems processing sensitive personal data, offering an incremental improvement by positioning surgical unlearning as an alternative to full retraining.
The paper tackles the problem of selectively revoking specific data modalities in multimodal sentiment analysis for privacy compliance, presenting Missing-by-Design (MBD) as a framework that achieves strong predictive performance under incomplete inputs and a practical privacy-utility trade-off.
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.