Slice or the Whole Pie? Utility Control for AI Models

TL;DR

This paper introduces NNObfuscator, a utility control mechanism that allows a single AI model to dynamically adjust its performance levels in real time, enabling efficient resource use and tiered access without multiple models.

Contribution

The paper presents NNObfuscator, a novel method for real-time performance adaptation in AI models, reducing the need for multiple models and improving resource management.

Findings

Successful implementation on various tasks including image classification and text-to-image generation.

Enables tiered access, balancing performance and resource consumption.

Maintains model adaptability across diverse applications.

Abstract

Training deep neural networks (DNNs) has become an increasingly resource-intensive task, requiring large volumes of labeled data, substantial computational power, and considerable fine-tuning efforts to achieve optimal performance across diverse use cases. Although pre-trained models offer a useful starting point, adapting them to meet specific user needs often demands extensive customization, and infrastructure overhead. This challenge grows when a single model must support diverse appli-cations with differing requirements for performance. Traditional solutions often involve training multiple model versions to meet varying requirements, which can be inefficient and difficult to maintain. In order to overcome this challenge, we propose NNObfuscator, a novel utility control mechanism that enables AI models to dynamically modify their performance according to predefined conditions. It is different from traditional methods that need separate models for each user. Instead, NNObfuscator allows a single model to be adapted in real time, giving you controlled access to multiple levels of performance. This mechanism enables model owners set up tiered access, ensuring that free-tier users receive a baseline level of performance while premium users benefit from enhanced capabilities. The approach improves resource allocation, reduces unnecessary computation, and supports sustainable business models in AI deployment. To validate our approach, we conducted experiments on multiple tasks, including image classification, semantic segmentation, and text to image generation, using well-established models such as ResNet, DeepLab, VGG16, FCN and Stable Diffusion. Experimental results show that NNObfuscator successfully makes model more adaptable, so that a single trained model can handle a broad range of tasks without requiring a lot of changes.