arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.13700cs.LGcs.CR
收藏

协同机器学习中鲁棒性与学习的冲突

On the Conflict of Robustness and Learning in Collaborative Machine Learning

EPFL(洛桑联邦理工学院)

Mathilde Raynal, Carmela Troncoso

AI总结:

本文形式化了协同机器学习中的两种鲁棒聚合器,证明基于距离和损失函数的聚合器均无法在保障安全性的同时不阻碍模型学习,揭示了鲁棒性与学习能力之间的固有冲突。

摘要:

协同机器学习(CML)允许参与者在保持训练数据隐私的同时联合训练机器学习模型。在许多将CML视为隐私问题解决方案的场景中(例如健康相关应用),安全性也是首要关注点。为了确保CML过程产生的模型即使在存在潜在不可信参与者的情况下也能输出正确且可靠的决策,研究人员提出使用鲁棒聚合器来过滤掉对训练过程产生负面影响的恶意贡献。在本研究中,我们形式化了文献中两种普遍存在的鲁棒聚合器形式。随后我们证明,两者都无法提供预期的保护:它们要么使用基于距离的度量,无法可靠地识别输入到训练中的恶意输入;要么使用基于损失函数行为的度量,这与CML参与者的学习能力产生了冲突,即它们无法在不阻碍学习的情况下消除被破坏的风险。

英文摘要:

Collaborative Machine Learning (CML) allows participants to jointly train a machine learning model while keeping their training data private. In many scenarios where CML is seen as the solution to privacy issues, such as health-related applications, safety is also a primary concern. To ensure that CML processes produce models that output correct and reliable decisions \emph{even in the presence of potentially untrusted participants}, researchers propose to use \textit{robust aggregators} to filter out malicious contributions that negatively influence the training process. In this work, we formalize the two prevalent forms of robust aggregators in the literature. We then show that neither can provide the intended protection: either they use distance-based metrics that cannot reliably identify malicious inputs to training; or use metrics based on the behavior of the loss function which create a conflict with the ability of CML participants to learn, i.e., they cannot eliminate the risk of compromise without preventing 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。

↑