CausShield: 通过因果表示学习实现样本重建鲁棒的纵向联邦学习
CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning
AI总结：
针对纵向联邦学习中样本重建攻击的防御问题，提出基于因果表示学习的CausShield方法，将共享表示分解为任务相关与无关部分，实现全周期隐私保护，理论证明收敛性，实验优于七种最新方法。
摘要：
纵向联邦学习（VFL）是一种分布式学习范式，利用跨孤立方的垂直划分特征，无需共享原始样本；然而，它仍然容易受到主动样本重建攻击。现有防御方法由于要么抑制任务相关信息的同时也抑制了隐私敏感特征，要么依赖端到端监督训练来收敛防御模块（这暴露了早期轮次的脆弱性），因此无法在模型效用和隐私保护之间实现令人满意的权衡。为了解决这一挑战，我们采用结构因果模型（SCM）的见解，构建了CausShield。从任务学习的角度来看，原始样本中的因果特征是那些直接相关且有助于学习目标的特征，而非因果特征与任务无关，但通常编码了样本特定的私有信息，从而促进了重建。重要的是，我们奠定了理论基础来证明这一见解。因此，CausShield将VFL中客户端与协调服务器之间的共享表示分解为任务相关和任务无关的组件，以确保全周期的隐私保护。然而，由于在保持模型效用的同时减轻隐私泄露的双重目标，这种分解本质上具有挑战性。我们通过一个精心制定的优化问题来解决这一问题，该问题通过无监督表示学习求解。我们进一步从理论上证明CausShield保持了标准VFL的收敛行为。大量实验将CausShield与七种最新方法（包括InvL (USENIX Security'25)）进行比较，并评估了对高级重建攻击（如URVFL (NDSS'25)）的鲁棒性。结果表明，CausShield在隐私保护、模型效用和计算效率方面始终表现优异。
英文摘要：
Vertical federated learning (VFL) is a distributed learning paradigm that leverages vertically partitioned features across isolated parties without sharing raw samples; however, it remains vulnerable to active sample reconstruction attacks. Existing defenses fail to achieve a satisfactory trade-off between model utility and privacy protection, due to either suppressing task-relevant information alongside privacy-sensitive features or relying on end-to-end supervised training to converge the defense module, which exposes the model to early-epoch vulnerability. To address this challenge, we adopt a structural causal model (SCM) insight and construct CausShield. From a task-learning standpoint, causal features within a raw sample are those that are directly relevant and contributory to the learning objective, whereas non-causal features are task-irrelevant but often encode sample-specific private information, thereby facilitating reconstruction. Importantly, we lay a theoretical foundation to prove this insight. CausShield thus decomposes the shared representations between the client and the coordinating server in VFL into task-relevant and task-irrelevant components to ensure full-cycle privacy protection. Nonetheless, the decomposition is inherently challenging due to the dual objectives of preserving model utility while mitigating privacy leakage. We address this via a carefully formulated optimization problem, which is solved through unsupervised representation learning. We further theoretically prove that CausShield preserves the convergence behavior of standard VFL. Extensive experiments compare CausShield against seven SOTAs, including InvL (USENIX Security'25), and evaluate robustness against advanced reconstruction attacks such as URVFL (NDSS'25). Results demonstrate that CausShield consistently outperforms in privacy protection, model utility, and computational efficiency.
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。
