SaTC: CORE: Small: Understanding and Mitigating the Security Risks of AutoML

SaTC：核心：小型：了解和减轻 AutoML 的安全风险

• 批准号: 2212323
• 负责人: Fenglong Ma
• 金额: $ 50万
• 依托单位: Pennsylvania State Univ University Park
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2212323&HistoricalAwards=false
• 关键词: SaTC; CORE; Small; Understanding; Mitigating

Automated machine learning (AutoML) represents a new machine learning paradigm that automates the pipeline from raw data to deployable models, enabling a much wider range of people to use machine learning techniques. However, each stage of this pipeline is subject to malicious attacks, which can lead to inaccurate or vulnerable models. This project’s goal is to understand how both the technologies underlying AutoML and the ways it is adopted change security risks around machine learning and how possible defenses to them change when using AutoML. The success of this project will not only improve the security of AutoML but also promote more principled practices of building and operating machine learning systems in general, while contributing to knowledge in the areas of security, machine learning, and human-computer interaction. The project has three main sub-goals: accounting for the full spectrum of security risks that arise around AutoML; understanding the fundamental factors that drive such risks; and designing for machine learning practitioners without extensive expertise. To accomplish these goals, the team will (i) better understand current practices around AutoML through user studies and interviews; (ii) empirically and analytically explore the security vulnerabilities of AutoML-generated models through assessing these models on widely used datasets; (iii) analyze the results of the first two activities to develop a comprehensive accounting of underlying factors such as standardization of algorithmic choices in the technology or over-reliance on automated metrics by users; and (iv) developing new principles, methodologies, and tools to mitigate the aforementioned risks. The team will also integrate the work into a number of college courses and conduct public outreach to raise awareness of the role machine learning plays in everyday life.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

自动化机器学习 (AutoML) 代表了一种新的机器学习范式，它自动化了从原始数据到可部署模型的流程，使更广泛的人能够使用机器学习技术。但是，该流程的每个阶段都会受到恶意攻击。可能会导致不准确或易受攻击的模型。该项目的目标是了解 AutoML 的底层技术及其采用方式如何改变机器学习的安全风险，以及使用 AutoML 时可能的防御措施如何改变。只提高AutoML的安全性还促进了构建和操作机器学习系统的更原则性实践，同时贡献了安全、机器学习和人机交互领域的知识。该项目具有三个主要子目标：涵盖所有领域。围绕 AutoML 出现的安全风险；了解导致此类风险的基本因素；以及为没有丰富专业知识的机器学习从业者进行设计，团队将 (i) 通过用户研究和访谈更好地了解 AutoML 的当前实践； ）以实证和分析的方式探索安全性通过在广泛使用的数据集上评估 AutoML 生成的模型的漏洞；(iii) 分析前两项活动的结果，以对技术算法选择的标准化或过度依赖自动化指标等潜在因素进行全面的核算； (iv) 开发新的原理、方法和工具来减轻所提到的风险。该团队还将把这项工作融入到一些大学课程中，并进行公众宣传，以提高人们对机器学习在日常生活中所扮演的角色的认识。 .这个奖项体现了通过使用基金会的智力价值和更广泛的影响审查标准进行评估，NSF 的法定使命被认为值得支持。

项目成果

Certified Edge Unlearning for Graph Neural Networks

经认证的图神经网络边缘消除学习

• 发表时间: 2023-01
• 期刊: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '23
• 作者: Wu, Kun;Shen, Jie;Ning, Yue;Wang, Ting;Wang, Hui W
• 通讯作者: Wang, Hui W

“Is your explanation stable?”: A Robustness Evaluation Framework for Feature Attribution

– 你的解释稳定吗？ –：特征归因的鲁棒性评估框架

• 发表时间: 2022-01
• 期刊: The 29th ACM Conference on Computer and Communications Security
• 作者: Gan, Y.;Mao, Y.;Zhang, X.;Ji, S.;Pu, Y.;Han, M.;Yin, J.;Wang, T.
• 通讯作者: Wang, T.

AutoML in The Wild: Obstacles, Workarounds, and Expectations

AutoML 实际应用：障碍、解决方法和期望

• DOI: 10.1145/3544548.3581082
• 发表时间: 2023-04
• 期刊: CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
• 作者: Sun, Yuan;Song, Qiurong;Gui, Xinning;Ma, Fenglong;Wang, Ting
• 通讯作者: Wang, Ting

The Dark Side of AutoML: Towards Architectural Backdoor Search

AutoML 的黑暗面：走向架构后门搜索

• 发表时间: 2023-01
• 期刊: The 11th International Conference on Learning Representations
• 作者: Pang, Ren;Li, Changjiang;Xi, Zhaohan;Ji, Shouling;Wang, Ting
• 通讯作者: Wang, Ting

AUTOMED: Automated Medical Risk Predictive Modeling on Electronic Health Records

AUTOMED：电子健康记录的自动化医疗风险预测模型

• DOI: 10.1109/bibm55620.2022.9995209
• 发表时间: 2022-12
• 期刊: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM
• 作者: Cui, Suhan;Wang, Jiaqi;Gui, Xinning;Wang, Ting;Ma, Fenglong
• 通讯作者: Ma, Fenglong