As machine learning (ML) technologies and applications are rapidly changing many domains of computing, security issues associated with ML are also emerging. In the domain of systems security, many endeavors have been made to ensure ML model and data confidentiality. ML computations are often inevitably performed in untrusted environments and entail complex multi-party security requirements. Hence, researchers have leveraged the Trusted Execution Environments (TEEs) to build confidential ML computation systems. This paper conducts a systematic and comprehensive survey by classifying attack vectors and mitigation in TEE-protected confidential ML computation in the untrusted environment, analyzes the multi-party ML security requirements, and discusses related engineering challenges.
相關內容
Recent times are witnessing rapid development in machine learning algorithm systems, especially in reinforcement learning, natural language processing, computer and robot vision, image processing, speech, and emotional processing and understanding. In tune with the increasing importance and relevance of machine learning models, algorithms, and their applications, and with the emergence of more innovative uses cases of deep learning and artificial intelligence, the current volume presents a few innovative research works and their applications in real world, such as stock trading, medical and healthcare systems, and software automation. The chapters in the book illustrate how machine learning and deep learning algorithms and models are designed, optimized, and deployed. The volume will be useful for advanced graduate and doctoral students, researchers, faculty members of universities, practicing data scientists and data engineers, professionals, and consultants working on the broad areas of machine learning, deep learning, and artificial intelligence.
The complexity of browsers has steadily increased over the years, driven by the continuous introduction and update of Web platform components, such as novel Web APIs and security mechanisms. Their specifications are manually reviewed by experts to identify potential security issues. However, this process has proved to be error-prone due to the extensiveness of modern browser specifications and the interplay between new and existing Web platform components. To tackle this problem, we developed WebSpec, the first formal security framework for the analysis of browser security mechanisms, which enables both the automatic discovery of logical flaws and the development of machine-checked security proofs. WebSpec, in particular, includes a comprehensive semantic model of the browser in the Coq proof assistant, a formalization in this model of ten Web security invariants, and a compiler turning the Coq model and the Web invariants into SMT-lib formulas. We showcase the effectiveness of WebSpec by discovering two new logical flaws caused by the interaction of different browser mechanisms and by identifying three previously discovered logical flaws in the current Web platform, as well as five in old versions. Finally, we show how WebSpec can aid the verification of our proposed changes to amend the reported inconsistencies affecting the current Web platform.
This Innovative Practice full paper describes a technical innovation for scalable teaching of cybersecurity hands-on classes using interactive learning environments. Hands-on experience significantly improves the practical skills of learners. However, the preparation and delivery of hands-on classes usually do not scale. Teaching even small groups of students requires a substantial effort to prepare the class environment and practical assignments. Further issues are associated with teaching large classes, providing feedback, and analyzing learning gains. We present our research effort and practical experience in designing and using learning environments that scale up hands-on cybersecurity classes. The environments support virtual networks with full-fledged operating systems and devices that emulate real-world systems. (...) Using the presented environments KYPO Cyber Range Platform and Cyber Sandbox Creator, we delivered the classes on-site or remotely for various target groups of learners (K-12, university students, and professional learners). The learners value the realistic nature of the environments that enable exercising theoretical concepts and tools. The instructors value time-efficiency when preparing and deploying the hands-on activities. Engineering and computing educators can freely use our software, which we have released under an open-source license. We also provide detailed documentation and exemplary hands-on training to help other educators adopt our teaching innovations and enable sharing of reusable components within the community.
Various forms of implications of artificial intelligence that either exacerbate or decrease racial systemic injustice have been explored in this applied research endeavor. Taking each thematic area of identifying, analyzing, and debating an systemic issue have been leveraged in investigating merits and drawbacks of using algorithms to automate human decision making in racially sensitive environments. It has been asserted through the analysis of historical systemic patterns, implicit biases, existing algorithmic risks, and legal implications that natural language processing based AI, such as risk assessment tools, have racially disparate outcomes. It is concluded that more litigative policies are needed to regulate and restrict how internal government institutions and corporations utilize algorithms, privacy and security risks, and auditing requirements in order to diverge from racially injustice outcomes and practices of the past.
In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone's daily life and profoundly altering the course of human society. The intention of developing AI is to benefit humans, by reducing human labor, bringing everyday convenience to human lives, and promoting social good. However, recent research and AI applications show that AI can cause unintentional harm to humans, such as making unreliable decisions in safety-critical scenarios or undermining fairness by inadvertently discriminating against one group. Thus, trustworthy AI has attracted immense attention recently, which requires careful consideration to avoid the adverse effects that AI may bring to humans, so that humans can fully trust and live in harmony with AI technologies. Recent years have witnessed a tremendous amount of research on trustworthy AI. 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. Trustworthy AI is a large and complex area, involving various dimensions. 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 & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems. We also discuss the accordant and conflicting interactions among different dimensions and discuss potential aspects for trustworthy AI to investigate in the future.
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.
Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. As the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning researches, as well as to summarize and interpret the mechanisms and the strategies in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Different from previous surveys, this survey paper reviews over forty representative transfer learning approaches from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, twenty representative transfer learning models are used for experiments. The models are performed on three different datasets, i.e., Amazon Reviews, Reuters-21578, and Office-31. And the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.
In recent years, mobile devices have gained increasingly development with stronger computation capability and larger storage. Some of the computation-intensive machine learning and deep learning tasks can now be run on mobile devices. To take advantage of the resources available on mobile devices and preserve users' privacy, the idea of mobile distributed machine learning is proposed. It uses local hardware resources and local data to solve machine learning sub-problems on mobile devices, and only uploads computation results instead of original data to contribute to the optimization of the global model. This architecture can not only relieve computation and storage burden on servers, but also protect the users' sensitive information. Another benefit is the bandwidth reduction, as various kinds of local data can now participate in the training process without being uploaded to the server. In this paper, we provide a comprehensive survey on recent studies of mobile distributed machine learning. We survey a number of widely-used mobile distributed machine learning methods. We also present an in-depth discussion on the challenges and future directions in this area. We believe that this survey can demonstrate a clear overview of mobile distributed machine learning and provide guidelines on applying mobile distributed machine learning to real applications.
This paper investigates to identify the requirement and the development of machine learning-based mobile big data analysis through discussing the insights of challenges in the mobile big data (MBD). Furthermore, it reviews the state-of-the-art applications of data analysis in the area of MBD. Firstly, we introduce the development of MBD. Secondly, the frequently adopted methods of data analysis are reviewed. Three typical applications of MBD analysis, namely wireless channel modeling, human online and offline behavior analysis, and speech recognition in the internet of vehicles, are introduced respectively. Finally, we summarize the main challenges and future development directions of mobile big data analysis.
Privacy is a major good for users of personalized services such as recommender systems. When applied to the field of health informatics, privacy concerns of users may be amplified, but the possible utility of such services is also high. Despite availability of technologies such as k-anonymity, differential privacy, privacy-aware recommendation, and personalized privacy trade-offs, little research has been conducted on the users' willingness to share health data for usage in such systems. In two conjoint-decision studies (sample size n=521), we investigate importance and utility of privacy-preserving techniques related to sharing of personal health data for k-anonymity and differential privacy. Users were asked to pick a preferred sharing scenario depending on the recipient of the data, the benefit of sharing data, the type of data, and the parameterized privacy. Users disagreed with sharing data for commercial purposes regarding mental illnesses and with high de-anonymization risks but showed little concern when data is used for scientific purposes and is related to physical illnesses. Suggestions for health recommender system development are derived from the findings.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191