Deep Intellectual Property Protection: A Survey
read the original abstract
Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields. The high performance of DNNs requires a huge amount of high-quality data, expensive computing hardware, and excellent DNN architectures that are costly to obtain. Therefore, trained DNNs are becoming valuable assets and must be considered the Intellectual Property (IP) of the legitimate owner who created them, in order to protect trained DNN models from illegal reproduction, stealing, redistribution, or abuse. Although being a new emerging and interdisciplinary field, numerous DNN model IP protection methods have been proposed. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of two mainstream DNN IP protection methods: deep watermarking and deep fingerprinting, with a proposed taxonomy. More than 190 research contributions are included in this survey, covering many aspects of Deep IP Protection: problem definition, main threats and challenges, merits and demerits of deep watermarking and deep fingerprinting methods, evaluation metrics, and performance discussion. We finish the survey by identifying promising directions for future research.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
GraphIP-Bench shows stealing GNNs is easy at moderate query budgets, most defenses fail to block or reliably trace extraction, and watermarks lose verification power on surrogates while heterophilic graphs are harder ...
-
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
-
CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
CSF is the first black-box method to attribute fine-tuned text-to-image models to original lineages via compositional semantic probes and Bayesian decisions across multiple model families.
-
SpanKey: Dynamic Key Space Conditioning for Neural Network Access Control
SpanKey injects keys from a learned subspace into network activations via additive or multiplicative maps to enable key-based access control for neural network inference.
-
SpanKey: Dynamic Key Space Conditioning for Neural Network Access Control
SpanKey injects keys from a learned subspace into intermediate activations to enable dynamic access control for neural network inference.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.