GraphTheft：量化图提示学习中的隐私风险
GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning
AI总结：
本文首次系统评估图提示学习（GPL）在三种攻击者能力下的隐私泄露风险，通过属性推断和链接推断攻击揭示其脆弱性，并探索拉普拉斯噪声扰动等防御机制，为图学习隐私保护提供新方向。
摘要：
图提示学习（Graph Prompt Learning，GPL）是图表示学习中的一种创新方法，通过在不改变底层预训练模型的情况下微调提示来实现特定任务的适配。尽管其日益受到关注，但GPL中固有的隐私风险尚未被探索。在本研究中，我们首次评估了GPL在三种攻击者能力下的隐私泄露：将GPL作为服务时的黑盒攻击，以及节点嵌入和提示表示可被第三方访问的场景。我们通过属性推断攻击（Attribute Inference Attacks，AIAs）和链接推断攻击（Link Inference Attacks，LIAs）评估了GPL的隐私脆弱性，发现在任何能力下，攻击者都能有效推断敏感节点的属性和关系，并且在某些数据集上推断成功率高达98%。重要的是，虽然针对特定提示（例如GPF-plus）的定向推断攻击保持了较高的成功率，但我们的分析表明，与传统图神经网络（GNNs）相比，GPL中的提示微调并未显著提高隐私风险。为了缓解这些风险，我们探索了防御机制，发现拉普拉斯噪声扰动可以显著降低推断成功率，但在隐私保护与模型性能之间取得平衡仍然具有挑战性。这项工作揭示了GPL中的关键隐私风险，为图学习中未来的隐私保护策略提供了新的见解和基础方向。
英文摘要：
Graph Prompt Learning (GPL) represents an innovative approach in graph representation learning, enabling task-specific adaptations by fine-tuning prompts without altering the underlying pre-trained model. Despite its growing prominence, the privacy risks inherent in GPL remain unexplored. In this study, we provide the first evaluation of privacy leakage in GPL across three attacker capabilities: black-box attacks when GPL as a service, and scenarios where node embeddings and prompt representations are accessible to third parties. We assess GPL's privacy vulnerabilities through Attribute Inference Attacks (AIAs) and Link Inference Attacks (LIAs), finding that under any capability, attackers can effectively infer the properties and relationships of sensitive nodes, and the success rate of inference on some data sets is as high as 98%. Importantly, while targeted inference attacks on specific prompts (e.g., GPF-plus) maintain high success rates, our analysis suggests that the prompt-tuning in GPL does not significantly elevate privacy risks compared to traditional GNNs. To mitigate these risks, we explored defense mechanisms, identifying that Laplacian noise perturbation can substantially reduce inference success, though balancing privacy protection with model performance remains challenging. This work highlights critical privacy risks in GPL, offering new insights and foundational directions for future privacy-preserving strategies in graph learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
