检测图神经网络是否被复制，即使模型结构和输出都不同。
COPYCOP: Ownership Verification for Graph Neural Networks
- 通过分析嵌入相似性识别伪装成其他模型的复制模型
- 在14个数据集上准确率超95%，抗多种攻击变换
- 适合保护GNN模型版权，尤其对抗恶意模仿者
给定两个输出节点嵌入的图神经网络（GNN），如何判断它们是否独立训练？攻击者可能专门训练一个GNN以模仿另一个GNN的嵌入。为掩盖这种关系，攻击模型可能对输出嵌入进行变换。两个GNN可具有不同的架构、权重和嵌入维度，攻击者还能转换嵌入。尽管条件严苛，我们提出的算法CopyCop仍能识别此类复制模型，而现有水印与指纹方法无法做到。我们还为CopyCop提供了理论保证。在14个数据集和5种GNN架构上的实验表明，CopyCop准确且对广泛攻击和变换具有鲁棒性。代码已公开：https://anonymous.4open.science/r/CopyCop-Graph-Ownership-Verification-8143/README.md
原文摘要 · Abstract (English)
Given two GNNs that output node embeddings, how can we determine if they were trained independently? An adversary could have trained one GNN specifically to mimic the other GNN's embeddings. To obscure this relationship between the GNNs, the adversarial GNN might then transform its output embeddings. The two GNNs could have different architectures, weights, and embedding dimensions, and the adversary can transform the embeddings. Despite these stringent conditions, our algorithm (named CopyCop) can identify such copycat GNNs, unlike existing watermarking and fingerprinting methods. We also provide theoretical guarantees for CopyCop. Finally, experiments on 14 datasets and 5 GNN architectures demonstrate that CopyCop is accurate and robust against a broad class of adversarial attacks and transformations. Code is available at: https://anonymous.4open.science/r/CopyCop-Graph-Ownership-Verification-8143/README.md
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。