检索结果-内蒙古大学图书馆

µVulDeePecker: A deep learning-based system for multiclass vulnerability detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zou, Deqing Wang, Sujuan Xu, Shouhuai Li, Zhen Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057 China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249 United States

Fine-grained software vulnerability detection is an important and challenging problem. Ideally, a detection system (or detector) not only should be able to detect whether or not a program contains vulnerabilities, but also should be able to pinpoint the type of a vulnerability in question. Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i.e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i.e., incapable of addressing multiclass classification). In this paper, we propose the first deep learning-based system for multiclass vulnerability detection, dubbed µVulDeePecker. The key insight underlying µVulDeePecker is the concept of code attention, which can capture information that can help pinpoint types of vulnerabilities, even when the samples are small. For this purpose, we create a dataset from scratch and use it to evaluate the effectiveness of µVulDeePecker. Experimental results show that µVulDeePecker is effective for multiclass vulnerability detection and that accommodating control-dependence (other than data-dependence) can lead to higher detection capabilities. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

VulDeeLocator: A deep learning-based fine-grained vulnerability detector

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Zhen Zou, Deqing Xu, Shouhuai Chen, Zhaoxuan Zhu, Yawei Jin, Hai The National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Cyber Security and Computer Hebei University Baoding071002 China The Department of Computer Science University of Colorado Colorado Springs CO80918 United States University of Texas San Antonio United States

Automatically detecting software vulnerabilities is an important problem that has attracted much attention from the academic research community. However, existing vulnerability detectors still cannot achieve the vulnerability detection capability and the locating precision that would warrant their adoption for real-world use. In this paper, we present a vulnerability detector that can simultaneously achieve a high detection capability and a high locating precision, dubbed Vulnerability Deep learning-based Locator (VulDeeLocator). In the course of designing VulDeeLocator, we encounter difficulties including how to accommodate semantic relations between the definitions of types as well as macros and their uses across files, how to accommodate accurate control flows and variable define-use relations, and how to achieve high locating precision. We solve these difficulties by using two innovative ideas: (i) leveraging intermediate code to accommodate extra semantic information, and (ii) using the notion of granularity refinement to pin down locations of vulnerabilities. When applied to 200 files randomly selected from three real-world software products, VulDeeLocator detects 18 confirmed vulnerabilities (i.e., true-positives). Among them, 16 vulnerabilities correspond to known vulnerabilities;the other two are not reported in the National Vulnerability Database (NVD) but have been "silently" patched by the vendor of Libav when releasing newer versions. Copyright © 2020, The Authors. All rights reserved.

关键词： Location

Robust design of web services supporting the home administration of drug infusion in pediatric oncology

学校读者我要写书评

暂无评论

Robust design of web services supporting the home administra...

13th International Conference on Axiomatic Design, ICAD 2019

作者： Parretti, Chiara Pourabbas, Elaheh Rolli, Fernando Pecoraro, Fabrizio Citti, Paolo Giorgetti, Alessandro Department of Innovation and Information Engineering Guglielmo Marconi University Via Plinio 44 Rome00193 Italy Institute for System Analysis and Computer Science A. Ruberti National Research Council Via dei Taurini 19 Rome00185 Italy Institute for Research on Population and Social Policies National Research Council Via Palestro 32 Rome00185 Italy

Cancer home care is a sector of particular relevance for the Italian health service. The budget ceilings imposed by public finance pose the need to reduce hospitalisation costs, moving patients from treatment to home care as much as possible. This is especially true in the field of pediatric oncology, where a protected family environment offers a variety of benefits to young patients and their families. However, in order to guarantee adequate assistance services, an integrated information system for management must be devised as the center of gravity of a coordinated network of, even heterogeneous, actors. This paper focuses on the identification and evolving development of web services for regulation and control of home administration of drug infusion in pediatric oncology. The Service Oriented Architecture (SOA) remains the software architecture of reference, where as the methodological approach is open to a reconsideration of the continuous improvement of the whole process in light of the ceaseless progress of medical science and information technology. In this paper, his goal is achieved by using a methodological design approach that combines the UML modeling based on Case Stories and the process optimization of Axiomatic Design. Case Stories allow the formalization of end users' requirements in UML language, easily interpreted by software developers. On the other hand, Axiomatic Design allows optimizing the design process by identifying the most robust solutions in terms of greater logical coherence and lesser systemic complexity. We analyze a case study focused on the design of web services supporting the home administration of drug infusion, for young cancer patients in home care. Then, we show how the UML-modeling methodology can be used to design new services on the basis of specific Use Cases. Finally, through theAxiomatic design approach we verify the proposed solutions, by identifying the robust set of web services to be implemented. © 2019 The Authors,

关键词： Web services

Clinical risk evaluation of medical device software: An axiomatic design-based methodology

学校读者我要写书评

暂无评论

Clinical risk evaluation of medical device software: An axio...

13th International Conference on Axiomatic Design, ICAD 2019

作者： Rolli, Fernando Pecoraro, Fabrizio Luzi, Daniela Ricci, Fabrizio L. Pourabbas, Elaheh Parretti, Chiara Department of Innovation and Information Engineering Guglielmo Marconi University Via Plinio 44 Rome00193 Italy Institute for Research on Population and Social Policies National Research Council Via Palestro 32 Rome00185 Italy Institute for System Analysis and Computer Science A. Ruberti National Research Council Via dei Taurini 19 Rome00185 Italy

The increasing complexity of medical device (MD) management software requires the adoption of new methodological approaches that pay particular attention to safety issues. The risk analysis is one of the key activities to be carried out by the manufacturer before the development of the software application as it determines the type of documentation to be provided as well as the activities to be performed to place the MD on the market. After the definition of software requirements and their iterative transformation into architectural items and/or units, the manufacturer defines the safety class of each item. The adoption of an axiomatic design approach facilitates this process. This combination of techniques helps to focus the design of medical device software on non-conformities with a clear link to clinical risk. This objective can be achieved by assessing the complexity of the system to be designed, both in terms of its functional size, and as a level of overall clinical risk. In this multi-dimensional perspective, the software effort expressed in function points provides an estimate of the development cost. While the clinical risk analysis allows to quickly identify critical areas, to intervene with the same promptness and to draft a management plan according to the regulations of the various control authorities. © 2019 The Authors, published by EDP sciences.

关键词： Risk assessment

Impact of Drug-Drug Interactions on Clinical Outcomes in Metastatic Melanoma Patients Treated With Combined BRAF/MEK Inhibitors: A Real-World Study

学校读者我要写书评

暂无评论

Pigment cell & melanoma research 2025年第4期38卷 e70026页

作者： Silvia Mezi Andrea Botticelli Giulia Pomati Simone Scagnoli Giulia Fiscon Federica de Galitiis Francesca Romana di Pietro Sofia Verkhovskaia Sasan Amirhassankhani Giovanna Gentile Maurizio Simmaco Bjoern Gohlke Robert Preissner Daniele Santini Paolo Marchetti Department of Radiological Science Oncology and Anatomical Pathology Faculty of Medicine and Dentistry "Sapienza University of Rome" and Unit Medical Oncology Policlinico Umberto I University Hospital Rome Italy. Department of Molecular Medicine Sapienza University of Rome Rome Italy. Department of Computer Control and Management Engineering "Antonio Ruberti" "Sapienza" University of Rome Rome Italy. Istituto Dermopatico Dell'immacolata IDI-IRCCS Rome Italy. Department of Urology S. Orsola-Malpighi Hospital University of Bologna Bologna Italy. Department of Neuroscience Mental Health and Sensory Organs (NESMOS) Faculty of Medicine and Psychology Sapienza University Rome Italy. Unit of Laboratory and Advanced Molecular Diagnostics Sant'Andrea University Hospital Rome Italy. Structural Bioinformatics Group Institute for Physiology Charité-University Medicine Berlin Berlin Germany. Department of Medico-Surgical Sciences and Biotechnology Polo Pontino Sapienza University of Rome Rome Italy.

The unique pharmacokinetics of BRAF and MEK inhibitors make patients vulnerable to drug-drug interactions (DDIs), which may compromise treatment efficacy in metastatic melanoma. This study evaluates the impact of DDIs on clinical outcomes in patients with metastatic melanoma treated with BRAF/MEK inhibitors. This multicenter, observational, retrospective study assessed DDIs using the Drug-PIN software. Associations between the Drug-PIN continuous score, Drug-PIN light, and treatment outscomes were analyzed along with the specific drugs involved in the DDIs. A total of 177 patients with BRAF-mutant metastatic melanoma undergoing BRAF/MEK inhibitor therapy were included. Of these, 94 patients (55.9%) were exposed to complex drug regimens related to comorbidities, supportive care, and symptom management. A significant change in Drug-PIN scores was observed before and after therapy initiation. Patients with low-grade DDIs demonstrated significantly longer median overall survival (OS) and progression-free survival (PFS) compared to those with high-grade DDIs (log-rank p = 0.0045 and p = 0.012, respectively); this observation was further validated by multiple regression analysis. By combining clinical and DDI data, we identified four patient subgroups with distinct prognoses, showing statistically significant differences in OS and PFS (log-rank p < 0.0001). The subgroup with the highest clinical risk and high DDI had markedly poorer outcomes (HR 2.87, 95% CI [1.7-4.8], p < 0.001). The drugs involved in high-level pharmacological interactions were analyzed. DDIs significantly contribute to poorer OS and PFS outcomes, independent of other clinical risk factors. Optimizing pharmacological regimens to minimize DDIs should be prioritized to enhance treatment efficacy in oncology. Prospective clinical trials are warranted to further validate the advantages of individualized, preemptive therapy optimization.

关键词： BRAF inhibitors BRAF mutation MEK inhibitors drug–drug interaction metastatic melanoma outcome prognostic factors

VerifyTL: Secure and verifiable collaborative transfer learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ma, Zhuoran Ma, Jianfeng Miao, Yinbin Liu, Ximeng Zheng, Wei Choo, Kim-Kwang Raymond Deng, Robert H. School of Cyber Engineering Xidian University Xi'an710071 China Shaanxi Key Laboratory of Network and System Security Xidian University Xi'an710071 China Key Laboratory of Information Security of Network Systems College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX78249 United States School of Information Systems Singapore Management University Singapore188065 Singapore

Getting access to labelled datasets in certain sensitive application domains can be challenging. Hence, one often resorts to transfer learning to transfer knowledge learned from a source domain with sufficient labelled data to a target domain with limited labelled data. However, most existing transfer learning techniques only focus on one-way transfer which brings no benefit to the source domain. In addition, there is the risk of a covert adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper we construct a secure and Verifiable collaborative Transfer Learning scheme, VerifyTL, to support two-way transfer learning over potentially untrusted datasets by improving knowledge transfer from a target domain to a source domain. Further, we equip VerifyTL with a cross transfer unit and a weave transfer unit employing SPDZ computation to provide privacy guarantee and verification in the two-domain setting and the multi-domain setting, respectively. Thus, VerifyTL is secure against covert adversary that can compromise up to n − 1 out of n data domains. We analyze the security of VerifyTL and evaluate its performance over two real-world datasets. Experimental results show that VerifyTL achieves significant performance gains over existing secure learning schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge management

Pocket diagnosis: Secure federated learning against poisoning attack in the cloud

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ma, Zhuoran Ma, Jianfeng Miao, Yinbin Liu, Ximeng Choo, Kim-Kwang Raymond Deng, Robert H. School of Cyber Engineering Xidian University Xi’an710071 China Guangxi Key Laboratory of Cryptography and Information Security Guilin541004 China Shaanxi Key Laboratory of Network and System Security Xidian University Xi’an710071 China Key Laboratory of Information Security of Network Systems College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX78249 United States School of Information Systems Singapore Management University 188065 Singapore

Federated learning has become prevalent in medical diagnosis due to its effectiveness in training a federated model among multiple health institutions (i.e., Data Islands (DIs)). However, increasingly massive DI-level poisoning attacks have shed light on a vulnerability in federated learning, which inject poisoned data into certain DIs to corrupt the availability of the federated model. Previous works on federated learning have been inadequate in ensuring the privacy of DIs and the availability of the final federated model. In this paper, we design a secure federated learning mechanism with multiple keys to prevent DI-level poisoning attacks for medical diagnosis, called SFPA. Concretely, SFPA provides privacy-preserving random forest-based federated learning by using the multi-key secure computation, which guarantees the confidentiality of DI-related information. Meanwhile, a secure defense strategy over encrypted locally-submitted models is proposed to defense DI-level poisoning attacks. Finally, our formal security analysis and empirical tests on a public cloud platform demonstrate the security and efficiency of SFPA as well as its capability of resisting DI-level poisoning attacks. Copyright © 2020, The Authors. All rights reserved.

关键词： Diagnosis

Fair Coresets and Streaming Algorithms for Fair k-means

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Schmidt, Melanie C., Schwiegelshohn C., Sohler Department of Computer Science Rheinische Friedrich-Wilhelms-Universität Bonn Bonn53111 Germany Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Roma RM00185 Italy Department of Computer Science TU Dortmund Dortmund44227 Germany

We study fair clustering problems as proposed by Chierichetti et al. [CKLV17]. Here, points have a sensitive attribute and all clusters in the solution are required to be balanced with respect to it (to counteract any form of data-inherent bias). Previous algorithms for fair clustering do not scale well. We show how to model and compute so-called coresets for fair clustering problems, which can be used to significantly reduce the input data size. We prove that the coresets are composable [IMMM14] and show how to compute them in a streaming setting. Furthermore, we propose a variant of Lloyd’s algorithm that computes fair clusterings and extend it to a fair k-means++ clustering algorithm. We implement these algorithms and provide empirical evidence that the combination of our approximation algorithms and the coreset construction yields a scalable algorithm for fair k-means clustering. Copyright © 2018, The Authors. All rights reserved.

关键词： Approximation algorithms

Performance variations of the Bayesian model of peer-assessment implemented in OpenAnswer response to modifications of the number of peers assessed and of the quality of the class 16

学校读者我要写书评

暂无评论

Performance variations of the Bayesian model of peer-assessm...

16th International Conference on Information Technology Based Higher Education and Training, ITHET 2017

作者： De Marsico, Maria Moschella, Luca Sterbini, Andrea Temperini, Marco Department of Computer Science Sapienza University of Rome Rome Italy Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Rome Italy

ISBN: (纸本)9781538639689

The paper presents a study of the performance variations of the Bayesian model of peer-assessment implemented in OpenAnswer, in terms of the grades prediction accuracy. OpenAnswer (OA) models a peer assessment session as a Bayesian network. For each student, a sub-network contains variables describing relevant aspects of both the individual cognitive state and the state of the current assessment session. Sub-networks are interconnected to each other to obtain the final one. Evidence propagated through the global network is represented by all the grades given by students to their peers, together with a subset of the teacher's corrections. Among the possible affecting factors, the paper reports about the investigation of the dependence of grades prediction performance on the quality of the class, i.e., the average level of proficiency of its students, and on the number of peers assessed by each student. The results show that both factors affect the accuracy of the inferred marks produced by the Bayesian network, when compared with the available ground-truth produced by teachers. © 2017 IEEE.

关键词： Students