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

You Can Use But Cannot Recognize: Preserving Visual Privacy...

Qiushi Li (Tsinghua University), Yan Zhang (Tsinghua University), Ju Ren (Tsinghua University), Qi Li (Tsinghua University), Yaoxue Zhang (Tsinghua University)

Read More

From Hardware Fingerprint to Access Token: Enhancing the Authentication...

Yue Xiao (Wuhan University), Yi He (Tsinghua University), Xiaoli Zhang (Zhejiang University of Technology), Qian Wang (Wuhan University), Renjie Xie (Tsinghua University), Kun Sun (George Mason University), Ke Xu (Tsinghua University), Qi Li (Tsinghua University)

Read More

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

Hengzhi Pei (UIUC), Jinyuan Jia (UIUC, Penn State), Wenbo Guo (UC Berkeley, Purdue University), Bo Li (UIUC), Dawn Song (UC Berkeley)

Read More

A Security and Usability Analysis of Local Attacks Against...

Tarun Kumar Yadav (Brigham Young University), Kent Seamons (Brigham Young University)

Read More