Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure
This addresses the challenge of secure data sharing for vision tasks among entities with limited sensitive data, though it appears incremental as it builds on existing pre-trained networks and poisoning concepts.
The paper tackles the problem of enabling multiple entities to share image data for training robust deep networks without visually disclosing sensitive contents, by introducing a Deep Poisoning Module that poisons features to prevent reconstruction while maintaining task functionality, with experimental results demonstrating efficacy in image classification.
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network. This paper introduces a new vision task where various entities share task-specific image data to enlarge each other's training data volume without visually disclosing sensitive contents (e.g. illegal images). Then, we present a new structure-based training regime to enable different entities learn task-specific and reconstruction-proof image representations for image data sharing. Specifically, each entity learns a private Deep Poisoning Module (DPM) and insert it to a pre-trained deep network, which is designed to perform the specific vision task. The DPM deliberately poisons convolutional image features to prevent image reconstructions, while ensuring that the altered image data is functionally equivalent to the non-poisoned data for the specific vision task. Given this equivalence, the poisoned features shared from one entity could be used by another entity for further model refinement. Experimental results on image classification prove the efficacy of the proposed method.