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 2202.13585cs.LGcs.CR
收藏

基于马尔可夫链蒙特卡洛的机器遗忘:遗忘需要遗忘的东西

Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten

National University of Singapore(新加坡国立大学);Trustwave(信波科技)

Quoc Phong Nguyen, Ryutaro Oikawa, Dinil Mon Divakaran, Mun Choon Chan, Bryan Kian Hsiang Low

摘要:

随着机器学习(ML)模型在许多现实应用中的使用越来越流行,模型维护需要解决一些实际挑战。其中一个挑战是“撤消”用于训练模型的特定数据集子集的效果。这个特定子集可能包含攻击者注入的恶意或敌对数据,这会影响模型性能。另一个原因可能是服务提供商需要删除与特定用户有关的数据以尊重用户的隐私。在这两种情况下,问题都是从训练模型中“遗忘”训练数据的特定子集,而不会导致从头开始重新训练整个模型的昂贵过程。为此,本文提出了一种基于马尔可夫链蒙特卡罗的机器遗忘(MCU)算法。MCU有助于有效和高效地从训练数据集的子集中学习训练模型。此外,我们证明了使用MCU,我们能够解释训练数据集的子集对模型预测的影响。因此,MCU对于检查数据子集以识别要删除的对抗性数据是有用的。同样,MCU可以用来从训练的ML模型中删除用户个人数据的血统,从而维护用户的“被遗忘权”。我们经验性地评估了我们提出的MCU算法在现实世界的网络钓鱼和糖尿病数据集上的性能。结果表明,MCU可以通过有效地去除训练数据集的一个子集的影响,并优于现有的算法,利用剩余的数据集,实现了理想的性能。

英文摘要:

As the use of machine learning (ML) models is becoming increasingly popular in many real-world applications, there are practical challenges that need to be addressed for model maintenance. One such challenge is to 'undo' the effect of a specific subset of dataset used for training a model. This specific subset may contain malicious or adversarial data injected by an attacker, which affects the model performance. Another reason may be the need for a service provider to remove data pertaining to a specific user to respect the user's privacy. In both cases, the problem is to 'unlearn' a specific subset of the training data from a trained model without incurring the costly procedure of retraining the whole model from scratch. Towards this goal, this paper presents a Markov chain Monte Carlo-based machine unlearning (MCU) algorithm. MCU helps to effectively and efficiently unlearn a trained model from subsets of training dataset. Furthermore, we show that with MCU, we are able to explain the effect of a subset of a training dataset on the model prediction. Thus, MCU is useful for examining subsets of data to identify the adversarial data to be removed. Similarly, MCU can be used to erase the lineage of a user's personal data from trained ML models, thus upholding a user's "right to be forgotten". We empirically evaluate the performance of our proposed MCU algorithm on real-world phishing and diabetes datasets. Results show that MCU can achieve a desirable performance by efficiently removing the effect of a subset of training dataset and outperform an existing algorithm that utilizes the remaining dataset.

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。

↑