Filters








3,628 Hits in 8.6 sec

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection [article]

Bingzhe Wu, Jintang Li, Junchi Yu, Yatao Bian, Hengtong Zhang, CHaochao Chen, Chengbin Hou, Guoji Fu, Liang Chen, Tingyang Xu, Yu Rong, Xiaolin Zheng (+8 others)
2022 arXiv   pre-print
In this survey, we provide a comprehensive review of recent leading approaches in the TwGL field from three dimensions, namely, reliability, explainability, and privacy protection.  ...  Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint.  ...  This survey provides a systematic and comprehensive overview of trustworthy graph learning (TwGL) from three fundamental aspects, i.e., reliability, explainability and privacy.  ... 
arXiv:2205.10014v2 fatcat:aobv34rwg5ehpka4fsuar2gm7i

Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context [article]

Ehsan Toreini, Mhairi Aitken, Kovila P. L. Coopamootoo, Karen Elliott, Vladimiro Gonzalez Zelaya, Paolo Missier, Magdalene Ng, Aad van Moorsel
2022 arXiv   pre-print
We conclude with an identification of open research problems, with a particular focus on the connection between trustworthy machine learning technologies and their implications for individuals and society  ...  As a consequence, we survey in this paper the main technologies with respect to all four of the FEAS properties, for data-centric as well as model-centric stages of the machine learning system life cycle  ...  We do this through a survey that considers technologies for trustworthy machine learning in relation to emerging policy frameworks.  ... 
arXiv:2007.08911v3 fatcat:gmswdvel6bdbvg5rvyzb2uygbu

A Survey on Trust Evaluation Based on Machine Learning

Jingwen Wang, Xuyang Jing, Zheng Yan, Yulong Fu, Witold Pedrycz, Laurence T. Yang
2020 ACM Computing Surveys  
In this article, we perform a thorough survey on trust evaluation based on machine learning. First, we cover essential prerequisites of trust evaluation and machine learning.  ...  It faces a number of severe issues such as lack of essential evaluation data, demand of big data process, request of simple trust relationship expression, and expectation of automation.  ...  Fourth, the security of trust evaluation is worth special efforts. In our survey, the issue of data privacy protection has not been touched.  ... 
doi:10.1145/3408292 fatcat:fem3px673bcfdltackc7bstxji

Machine Learning for Security in Vehicular Networks: A Comprehensive Survey [article]

Anum Talpur, Mohan Gurusamy
2021 arXiv   pre-print
Machine Learning (ML) has emerged as an attractive and viable technique to provide effective solutions for a wide range of application domains.  ...  In this paper, we present a comprehensive survey of ML-based techniques for different security issues in vehicular networks.  ...  Privacy Protection Privacy is a means of protecting the sensitive information of vehicles from attackers.  ... 
arXiv:2105.15035v2 fatcat:5z6aqlvosjgf3o3amts3k6toxu

Federated Learning for Smart Healthcare: A Survey [article]

Dinh C. Nguyen, Quoc-Viet Pham, Pubudu N. Pathirana, Ming Ding, Aruna Seneviratne, Zihuai Lin, Octavia A. Dobre, Won-Joo Hwang
2021 arXiv   pre-print
Accordingly, we provide a comprehensive survey on the use of FL in smart healthcare.  ...  Several recent FL-based smart healthcare projects are analyzed, and the key lessons learned from the survey are also highlighted.  ...  , while a degree of privacy protection is achieved.  ... 
arXiv:2111.08834v1 fatcat:jmex4e25rbgy3bk67iolrj4uee

Trustworthy Graph Neural Networks: Aspects, Methods and Trends [article]

He Zhang, Bang Wu, Xingliang Yuan, Shirui Pan, Hanghang Tong, Jian Pei
2022 arXiv   pre-print
Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering  ...  In this survey, we introduce basic concepts and comprehensively summarise existing efforts for trustworthy GNNs from six aspects, including robustness, explainability, privacy, fairness, accountability  ...  BETWEEN OUR SURVEY AND REPRESENTATIVE SURVEYS Scope Perspective Surveys Generic GNNs Trustworthiness AI GNNs Robust-ness Explain-ability Privacy Fairness Account-ability Environment-al Well-being Relations  ... 
arXiv:2205.07424v1 fatcat:f3iul7soqvgzbgaeqw7nhypbju

AI System Engineering—Key Challenges and Lessons Learned

Lukas Fischer, Lisa Ehrlinger, Verena Geist, Rudolf Ramler, Florian Sobiezky, Werner Zellinger, David Brunner, Mohit Kumar, Bernhard Moser
2020 Machine Learning and Knowledge Extraction  
The main challenges are discussed together with the lessons learned from past and ongoing research along the development cycle of machine learning systems.  ...  and ethical aspects. the analysis outlines a fundamental theory-practice gap which superimposes the challenges of AI system engineering at the level of data quality assurance, model building, software  ...  The complex of problems that derives from this aspect of artificial intelligence for explainability, transparency, trustworthiness, and so forth, is generally described with the term Explainable Artificial  ... 
doi:10.3390/make3010004 fatcat:35qfecqrn5auxc3epcjodxuez4

Trustworthy AI: A Computational Perspective [article]

Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, Jiliang Tang
2021 arXiv   pre-print
In this survey, we present a comprehensive survey of trustworthy AI from a computational perspective, to help readers understand the latest technologies for achieving trustworthy AI.  ...  In this work, we focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability  ...  Most importantly, a versatile and reliable system design for achieving privacy protection and different techniques should be integrated to enhance the trustworthiness of AI systems.  ... 
arXiv:2107.06641v3 fatcat:ymqaxvzsoncqrcosj5mxcvgsuy

A Bidder Behavior Learning Intelligent System for Trust Measurement

El-Sayed M.TowfekEl-kenawy, Ali Ibraheem El-Desoky, Amany M. Sarhan
2014 International Journal of Computer Applications  
The online auctions face a serious problem of trust among the participants where users have no information about the others, and have no relations among them except the commercial transactions; this allows  ...  We proposed a framework depend on "Bidder Behavior" consist of three algorithms the first " Bidder Increase Price Behavior"(BIPB), the second "Search In Stored Data Base"(SSDB) and the third "Person Recursive  ...  transactions as a social network graph which edges length and thickness as a function of strength and goodness.  ... 
doi:10.5120/15521-4225 fatcat:q3do4zfu3nfj3cj45ur3njcgji

Privacy-preserving Distributed Machine Learning via Local Randomization and ADMM Perturbation [article]

Xin Wang, Hideaki Ishii, Linkang Du, Peng Cheng, Jiming Chen
2019 arXiv   pre-print
Further, the ADMM algorithm is perturbed through a combined noise-adding method, which simultaneously preserves privacy for users' less sensitive information and strengthens the privacy protection of the  ...  With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks.  ...  To protect privacy of feature vectors against less trustworthy servers, we further use a combined noise-adding method to perturb the ADMM algorithm, which also strengthens the privacy guarantee of users  ... 
arXiv:1908.01059v2 fatcat:6n7ex5esh5cg3hthdpic6zoqje

Blockchain-based Federated Learning: A Comprehensive Survey [article]

Zhilin Wang, Qin Hu
2021 arXiv   pre-print
However, issues of privacy and scalability will constrain the development of machine learning.  ...  In this paper, we conduct a comprehensive survey of the literature on blockchained FL (BCFL).  ...  [20] surveys the research related to the privacy issues of FL, illustrating several attacks which will lead to the leakage of data privacy, e.g., membership inference attack and GAN-based(a deep learning  ... 
arXiv:2110.02182v1 fatcat:sm2mtftvq5fodgkfdhcan55n3q

Deep Learning Application in Security and Privacy -- Theory and Practice: A Position Paper [article]

Julia A. Meister, Raja Naeem Akram, Konstantinos Markantonakis
2018 arXiv   pre-print
We also put forward potential challenges a DL based security and privacy protection technique has to overcome.  ...  Such infrastructure faces a diverse range of challenges to its operations that include security, privacy, resilience, and quality of services.  ...  Security and Privacy by Deep Learning In this section, we survey the types of security and privacy services and applications in which DL is deployed successfully -as represented by academic literature.  ... 
arXiv:1812.00190v1 fatcat:jkv2z6mjmvcbvo2l3ptassfpp4

A Survey on Trustworthy Recommender Systems [article]

Yingqiang Ge, Shuchang Liu, Zuohui Fu, Juntao Tan, Zelong Li, Shuyuan Xu, Yunqi Li, Yikun Xian, Yongfeng Zhang
2022 arXiv   pre-print
In this survey, we will introduce techniques related to trustworthy and responsible recommendation, including but not limited to explainable recommendation, fairness in recommendation, privacy-aware recommendation  ...  Through this survey, we hope to deliver readers with a comprehensive view of the research area and raise attention to the community about the importance, existing research achievements, and future research  ...  Explainable AI and Privacy. Some existing privacy protection techniques are built based on deep learning models that are difficult to interpret.  ... 
arXiv:2207.12515v1 fatcat:lsnuwdtl5rboznmhhux2n5y5om

Towards Security Threats of Deep Learning Systems: A Survey [article]

Yingzhe He and Guozhu Meng and Kai Chen and Xingbo Hu and Jinwen He
2020 arXiv   pre-print
In order to unveil the security weaknesses and aid in the development of a robust deep learning system, we undertake an investigation on attacks towards deep learning, and analyze these attacks to conclude  ...  However, deep learning systems are suffering several inherent weaknesses, which can threaten the security of learning models. Deep learning's wide use further magnifies the impact and consequences.  ...  The privacy protection terms used in related articles are explained in detail in Section 8.6.  ... 
arXiv:1911.12562v2 fatcat:m3lyece44jgdbp6rlcpj6dz2gm

Deep Learning for Android Malware Defenses: a Systematic Literature Review [article]

Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu
2022 arXiv   pre-print
In recent years, a dominant research field called deep learning (DL), which provides a powerful feature abstraction ability, has demonstrated a compelling and promising performance in a variety of areas  ...  In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment.  ...  CCS Concepts: • Security and privacy → Malware and its mitigation; Software security engineering; • General and reference → Surveys and overviews.  ... 
arXiv:2103.05292v2 fatcat:qruddq4gknfq7jx5wyrk5qu2eu
« Previous Showing results 1 — 15 out of 3,628 results