PriFU: Capturing Task-Relevant Information Without Adversarial Learning
Abstract: As machine learning advances, machine learning as a service (MLaaS) in the cloud brings convenience to human lives but also privacy risks, as powerful neural networks used for generation, classification or other tasks can also become privacy snoopers. This motivates privacy preservation in the inference phase. Many approaches for preserving privacy in the inference phase introduce multi-objective functions, training models to remove specific private information from users' uploaded data. Although effective, these adversarial learning-based approaches suffer not only from convergence difficulties, but also from limited generalization beyond the specific privacy for which they are trained. To address these issues, we propose a method for privacy preservation in the inference phase by removing task-irrelevant information, which requires no knowledge of the privacy attacks nor introduction of adversarial learning. Specifically, we introduce a metric to distinguish task-irrelevant information from task-relevant information, and achieve more efficient metric estimation to remove task-irrelevant features. The experiments demonstrate the potential of our method in several tasks.
Relevance To Conference: We present a simple and universal data processing to preserve privacy while uploading data to use machine learning as a service (MLaaS) in the cloud. This data processing can be applied to multimedia/multimodal data.
Primary Subject Area: [Experience] Multimedia Applications
Secondary Subject Area: [Content] Media Interpretation
Submission Number: 3050
Loading