Bang Wu (CSIRO's Data61/Monash University), He Zhang (Monash University), Xiangwen Yang (Monash University), Shuo Wang (CSIRO's Data61/Shanghai Jiao Tong University), Minhui Xue (CSIRO's Data61), Shirui Pan (Griffith University), Xingliang Yuan (Monash University)

The emergence of Graph Neural Networks (GNNs) in graph data analysis and their deployment on Machine Learning as a Service platforms have raised critical concerns about data misuse during model training. This situation is further exacerbated due to the lack of transparency in local training processes, potentially leading to the unauthorized accumulation of large volumes of graph data, thereby infringing on the intellectual property rights of data owners. Existing methodologies often address either data misuse detection or mitigation, and are primarily designed for local GNN models rather than cloud-based MLaaS platforms. These limitations call for an effective and comprehensive solution that detects and mitigates data misuse without requiring exact training data while respecting the proprietary nature of such data. This paper introduces a pioneering approach called GraphGuard, to tackle these challenges. We propose a training-data-free method that not only detects graph data misuse but also mitigates its impact via targeted unlearning, all without relying on the original training data. Our innovative misuse detection technique employs membership inference with radioactive data, enhancing the distinguishability between member and non-member data distributions. For mitigation, we utilize synthetic graphs that emulate the characteristics previously learned by the target model, enabling effective unlearning even in the absence of exact graph data. We conduct comprehensive experiments utilizing four real-world graph datasets to demonstrate the efficacy of GraphGuard in both detection and unlearning. We show that GraphGuard attains a near-perfect detection rate of approximately 100% across these datasets with various GNN models. In addition, it performs unlearning by eliminating the impact of the unlearned graph with a marginal decrease in accuracy (less than 5%).

View More Papers

Facilitating Threat Modeling by Leveraging Large Language Models

Isra Elsharef, Zhen Zeng (University of Wisconsin-Milwaukee), Zhongshu Gu (IBM Research)

Read More

Faster and Better: Detecting Vulnerabilities in Linux-based IoT Firmware...

Zicong Gao (State Key Laboratory of Mathematical Engineering and Advanced Computing), Chao Zhang (Tsinghua University), Hangtian Liu (State Key Laboratory of Mathematical Engineering and Advanced Computing), Wenhou Sun (Tsinghua University), Zhizhuo Tang (State Key Laboratory of Mathematical Engineering and Advanced Computing), Liehui Jiang (State Key Laboratory of Mathematical Engineering and Advanced Computing), Jianjun Chen (Tsinghua…

Read More

DeGPT: Optimizing Decompiler Output with LLM

Peiwei Hu (Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China), Ruigang Liang (Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China), Kai Chen (Institute of Information Engineering, Chinese Academy of Sciences, China)

Read More

A Unified Symbolic Analysis of WireGuard

Pascal Lafourcade (Universite Clermont Auvergne), Dhekra Mahmoud (Universite Clermont Auvergne), Sylvain Ruhault (Agence Nationale de la Sécurité des Systèmes d'Information)

Read More