Problem
Research questions and friction points this paper is trying to address.
Privacy-Enhancing Technologies
Computer Vision
Task Performance
Data Protection
Image Classification
Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
🤖 AI Summary
研究提出一种计算感知的多任务协议，用于评估隐私增强技术在模型训练中的效果，通过轻量级代理任务解决仅依赖图像分类评估的局限性。
📝 Abstract
Privacy-Enhancing Technologies (PETs) in computer vision often rely on noise or image perturbations to protect visual data while securely processing it, creating a trade-off between task performance and protection. This trade-off is commonly evaluated using image classification, which primarily captures semantic separability and remains robust despite significant geometric, spatial layout or local boundary alterations. As a result, it is too simplistic as a proxy for generic vision tasks. Exhaustive downstream-task evaluation, however, is computationally expensive because models must often be trained for each PET transformation and parameter setting. We therefore propose a compute-aware multi-task protocol for evaluating PETs in model training. It combines lightweight proxy tasks that target complementary aspects of visual structure while remaining simple and fast to compute. Across irreversible privacy transformations, key-based block primitives, and learnable image encryption schemes, we demonstrate that PETs with similar classification accuracy can differ substantially on other tasks. The outcomes highlight the need for PET evaluation protocols that move beyond classification-only reporting.
Innovation
Methods, ideas, or system contributions that make the work stand out.
compute-aware multi-task protocol
lightweight proxy tasks
privacy-enhancing technologies (PETs)
visual structure
🔎 Similar Papers
No similar papers found.
