Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice最新文献_第2页

MC2: A Secure Collaborative Computation Platform MC2:一个安全的协同计算平台

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-11-09 DOI: 10.1145/3411501.3418609

R. A. Popa

引用次数: 0

Introduction to Secure Collaborative Intelligence (SCI) Lab 安全协同智能(SCI)实验室简介

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-11-09 DOI: 10.1145/3411501.3418606

Pu Duan

{"title":"Introduction to Secure Collaborative Intelligence (SCI) Lab","authors":"Pu Duan","doi":"10.1145/3411501.3418606","DOIUrl":"https://doi.org/10.1145/3411501.3418606","url":null,"abstract":"With the rapid development of technology, user privacy and data security are drawing much attention over the recent years. On one hand, how to protect user privacy while making use of customers? data is a challenging task. On the other hand, data silos are becoming one of the most prominent issues for the society. How to bridge these isolated data islands to build better AI and BI systems while meeting the data privacy and regulatory compliance requirements has imposed great challenges. Secure Collaborative Intelligence (SCI) lab at Ant Group dedicates to leverage multiple privacy-preserving technologies on AI and BI to solve these challenges. The goal of SCI lab is to build enterprise-level solutions that allow multiple data owners to achieve joint risk control, joint marketing, joint data analysis and other cross-organization collaboration scenarios without compromising information privacy or violating any related security policy. Compared with other solution providers, SCI lab has been working with top universities and research organizations to build the first privacy-preserving open platform for collaborative intelligence computation in the world. It is the first platform that combines all three cutting-edge privacy-preserving technologies, secure multi-party computation (MPC), differential privacy (DP) and trusted execution environment (TEE) that are based on cryptography, information theory and computer hardware respectively, on multi-party AI and BI collaboration scenarios. During multi-party collaboration, all inputs, computations and results are protected under specific security policy dedicatedly designed for each data owner. At this time, the platform has been applied to various business scenarios in Ant group and Alibaba Group, including joint lending, collaborative data analysis, joint payment fraud detection, etc. More than 20 financial organizations, have been benefited from the secure data collaboration and computing services provided by SCI lab.","PeriodicalId":116231,"journal":{"name":"Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134103402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Adversarial Detection on Graph Structured Data 图结构数据的对抗检测

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-11-09 DOI: 10.1145/3411501.3419424

Jinyin Chen, Huiling Xu, Jinhuan Wang, Qi Xuan, Xuhong Zhang

{"title":"Adversarial Detection on Graph Structured Data","authors":"Jinyin Chen, Huiling Xu, Jinhuan Wang, Qi Xuan, Xuhong Zhang","doi":"10.1145/3411501.3419424","DOIUrl":"https://doi.org/10.1145/3411501.3419424","url":null,"abstract":"Graph Neural Networks (GNNs) has achieved tremendous development on perceptual tasks in recent years, such as node classification, graph classification, link prediction, etc. However, recent studies show that deep learning models of GNNs are incredibly vulnerable to adversarial attacks, so enhancing the robustness of such models remains a significant challenge. In this paper, we propose a subgraph based adversarial sample detection against adversarial perturbations. To the best of our knowledge, this is the first work on the adversarial detection in the deep-learning graph classification models, using the Subgraph Networks (SGN) to restructure the graph's features. Moreover, we develop the joint adversarial detector to cope with the more complicated and unknown attacks. Specifically, we first explain how adversarial attacks can easily fool the models and then show that the SGN can facilitate the distinction of adversarial examples generated by state-of-the-art attacks. We experiment on five real-world graph datasets using three different kinds of attack strategies on graph classification. Our empirical results show the effectiveness of our detection method and further explain the SGN's capacity to tell apart malicious graphs.","PeriodicalId":116231,"journal":{"name":"Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115320108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

CryptoSPN: Expanding PPML beyond Neural Networks CryptoSPN:将PPML扩展到神经网络之外

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-11-01 DOI: 10.1145/3411501.3419417

Amos Treiber, Alejandro Molina, Christian Weinert, T. Schneider, K. Kersting

{"title":"CryptoSPN: Expanding PPML beyond Neural Networks","authors":"Amos Treiber, Alejandro Molina, Christian Weinert, T. Schneider, K. Kersting","doi":"10.1145/3411501.3419417","DOIUrl":"https://doi.org/10.1145/3411501.3419417","url":null,"abstract":"The ubiquitous deployment of machine learning (ML) technologies has certainly improved many applications but also raised challenging privacy concerns, as sensitive client data is usually processed remotely at the discretion of a service provider. Therefore, privacy-preserving machine learning (PPML) aims at providing privacy using techniques such as secure multi-party computation (SMPC). Recent years have seen a rapid influx of cryptographic frameworks that steadily improve performance as well as usability, pushing PPML towards practice. However, as it is mainly driven by the crypto community, the PPML toolkit so far is mostly restricted to well-known neural networks (NNs). Unfortunately, deep probabilistic models rising in the ML community that can deal with a wide range of probabilistic queries and offer tractability guarantees are severely underrepresented. Due to a lack of interdisciplinary collaboration, PPML is missing such important trends, ultimately hindering the adoption of privacy technology. In this work, we introduce CryptoSPN, a framework for privacy-preserving inference of sum-product networks (SPNs) to significantly expand the PPML toolkit beyond NNs. SPNs are deep probabilistic models at the sweet-spot between expressivity and tractability, allowing for a range of exact queries in linear time. In an interdisciplinary effort, we combine techniques from both ML and crypto to allow for efficient, privacy-preserving SPN inference via SMPC. We provide CryptoSPN as open source and seamlessly integrate it into the SPFlow library (Molina et al., arXiv 2019) for practical use by ML experts. Our evaluation on a broad range of SPNs demonstrates that CryptoSPN achieves highly efficient and accurate inference within seconds for medium-sized SPNs.","PeriodicalId":116231,"journal":{"name":"Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132521792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Secure Collaborative Training and Inference for XGBoost XGBoost的安全协同训练和推理

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-10-06 DOI: 10.1145/3411501.3419420

Andrew Law, Chester Leung, Rishabh Poddar, R. A. Popa, Chenyu Shi, Octavian Sima, Chaofan Yu, Xingmeng Zhang, Wenting Zheng

引用次数: 21

Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy 非隐私非公平:数据不平衡对差异隐私中效用与公平的影响

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-09-10 DOI: 10.1145/3411501.3419419

Tom Farrand, FatemehSadat Mireshghallah, Sahib Singh, Andrew Trask

引用次数: 49

MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference MP2ML:用于私有推理的混合协议机器学习框架

Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice Pub Date : 2020-08-01 DOI: 10.1145/3411501.3419425

Fabian Boemer, Rosario Cammarota, Daniel Demmler, T. Schneider, Hossein Yalame

引用次数: 10