CoreLocker: Neuron-level Usage Control
Zihan Wang, Zhongkui Ma, Xinguo Feng, Ruoxi Sun, Hu Wang, Minhui Xue
IEEE Symposium on Security and Privacy 2024 · Day 2 · Continental Ballroom 5
The presented talk, "CoreLocker: Neuron-level Usage Control," by Zihan Wang and collaborators, introduces a novel framework designed to protect and monetize the intellectual property inherent in Deep Neural Networks (DNNs). Given the astronomical resources—including vast datasets, immense computational power, and sophisticated architectural designs—required to develop state-of-the-art AI models like GPT-3, which demanded 355 GPU years and an estimated $4.6 million for a single training run, these models represent incredibly valuable assets. The potential returns are equally staggering, as exemplified by ChatGPT's rapid ascent to 100 million active users within two months and generating $80 million per month for OpenAI.
AI review
CoreLocker delivers a genuinely novel, neuron-level method for controlling DNN model utility, allowing owners to create tiered access and protect IP without retraining. By exploiting "impact concentration" of weights and providing strong theoretical and empirical validation, it offers a pragmatic and powerful solution for AI model monetization and security. This is real research that directly solves a critical industry problem.