GENIE: Watermarking Graph Neural Networks for Link Prediction

2024-06-07 · Venkata Sai Pranav Bachina, Ankit Gangwal, Aaryan Ajay Sharma, Charu Sharma

Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed within Machine Learning as a Service (MLaaS) necessitates robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for Deep Neural Networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Previous works on GNN watermarking have primarily focused on node and graph classification, overlooking Link Prediction (LP). In this paper, we propose GENIE (watermarking Graph nEural Networks for lInk prEdiction), the first-ever scheme to watermark GNNs for LP. GENIE creates a novel backdoor for both node-representation and subgraph-based LP methods, utilizing a unique trigger set and a secret watermark vector. Our OD scheme is equipped with Dynamic Watermark Thresholding (DWT), ensuring high verification probability (>99.99%) while addressing practical issues in existing watermarking schemes. We extensively evaluate GENIE across 4 model architectures (i.e., SEAL, GCN, GraphSAGE and NeoGNN) and 7 real-world datasets. Furthermore, we validate the robustness of GENIE against 11 state-of-the-art watermark removal techniques and 3 model extraction attacks. We also show GENIE's resilience against ownership piracy attacks. Finally, we discuss a defense strategy to counter adaptive attacks against GENIE.

📄 PDF Abstract BibTeX arXiv:2406.04805

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackDrug Discovery Graph Classification Link Prediction Model extraction Node Classification Prediction

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

GraphSAGE GraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen…

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Genie: A new, fast, and outlier-resistant hierarchical clustering algorithm

2022-09-13 · Marek Gagolewski, Maciej Bartoszuk, Anna Cena

The time needed to apply a hierarchical clustering algorithm is most often dominated by the number of computations of a pairwise dissimilarity measure. Such a constraint, for larger data sets, puts at a disadvantage the …

Clustering

Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise

2022-12-22 · Zhenghao Lin, Yeyun Gong, Yelong Shen, Tong Wu 외

In this paper, we introduce a novel dIffusion language modEl pre-training framework for text generation, which we call GENIE. GENIE is a large-scale pretrained diffusion language model that consists of an encoder and a d…

Decoder Denoising Language Modeling Language Modelling+1

Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design

2025-11-24 · Bruno Jacob, Khushbu Agarwal, Marcel Baer, Peter Rice 외 arxiv

We present Genie-CAT, a tool-augmented large-language-model (LLM) system designed to accelerate scientific hypothesis generation in protein design. Using metalloproteins (e.g., ferredoxins) as a case study, Genie-CAT int…

Protein Design

GeniePath: Graph Neural Networks with Adaptive Receptive Paths

2018-02-03 · Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou 외

We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. In GeniePath, we propose an adaptive path layer consists of two complement…

Buffer-aware Wireless Scheduling based on Deep Reinforcement Learning

2019-11-13 · Chen Xu, Jian Wang, Tianhang Yu, Chuili Kong 외

In this paper, the downlink packet scheduling problem for cellular networks is modeled, which jointly optimizes throughput, fairness and packet drop rate. Two genie-aided heuristic search methods are employed to explore …

Deep Reinforcement Learning Fairness Heuristic Search reinforcement-learning+3