发布求助
文献互助 智能选刊 最新文献

2021 Ivannikov Memorial Workshop (IVMEM)最新文献

筛选
英文 中文
A Survey of Open-source Tools for FPGA-based Inference of Artificial Neural Networks 基于fpga的人工神经网络推理开源工具综述
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00015
M. Lebedev, P. Belecky
{"title":"A Survey of Open-source Tools for FPGA-based Inference of Artificial Neural Networks","authors":"M. Lebedev, P. Belecky","doi":"10.1109/ivmem53963.2021.00015","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00015","url":null,"abstract":"During the recent years artificial neural networks have become a great part of everyday life. One of the big problems in AI is acceleration of neural network inference using different hardware: from CPUs and GPUs to FPGAs and ASICs. Many open-source tools have been proposed for this purpose. This article contains a review of a range of open-source tools for neural network optimization, acceleration and hardware synthesis. Tools of three types have been chosen for evaluation: 1) translating neural network models into synthesizable C; 2) accelerating neural network models using custom hardware accelerators; 3) synthesizing Verilog from neural network models. Some of the tools have been tested using five simple neural network examples. Intel CPU, NVIDIA GPU and Cyclone V FPGA hardware platforms have been used for evaluation. Results show that the tested tools can successfully process neural network models and optimize them for CPU and GPU execution, whereas FPGA execution results are controversial.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134123142","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: 3
Futag: Automated fuzz target generator for testing software libraries Futag:用于测试软件库的自动模糊目标生成器
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00021
Chi Thien Tran, S. Kurmangaleev
{"title":"Futag: Automated fuzz target generator for testing software libraries","authors":"Chi Thien Tran, S. Kurmangaleev","doi":"10.1109/ivmem53963.2021.00021","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00021","url":null,"abstract":"Recently, Fuzzing is one of the most successful techniques to expose bugs in software. For testing large programs or large codebase with many features and entry-points, the creation of fuzz-targets remains a big challenge. In this paper, we introduce Futag – an automated fuzz target generator for testing software libraries. This approach uses static analysis to collect information about source code: data type definitions, dependencies of types, definitions of functions, etc. Futag has found many vulnerabilities in latest version of popular libraries such as: libopenssl, libpng, libjson-c, liblxml2.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131111658","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
Detection of Missed Links in Large Legal Corpora 大型法律语料库中缺失链接的检测
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00010
D. Devyatkin, Yana Pogorelskaya, V. Yadrintsev, I. Sochenkov
{"title":"Detection of Missed Links in Large Legal Corpora","authors":"D. Devyatkin, Yana Pogorelskaya, V. Yadrintsev, I. Sochenkov","doi":"10.1109/ivmem53963.2021.00010","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00010","url":null,"abstract":"Legal texts have a large number of explicit and implicit links to other documents. Extraction of those links would help to systematize and analyze lawmaking activity better. Legal documents are often multi-topic and fragmented, making standard topical similarity search methods useless to reveal those links. In this paper, we propose Siamese network-based approaches, which can tackle that problem. Our approaches incorporate SentenceBERT and Doc2Vec models and generate document-level embeddings, which can be helpful to build a large-scale legal information retrieval system. The experiments on Russian and multilingual legal corpora confirm the applicability of the proposed methods. Namely, SentenceBERT-based models show the best performance, although they have to be fine-tuned on a multilingual labeled corpus.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116684653","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
Evaluation of interpretability methods for adversarial robustness on real-world datasets 对真实世界数据集的对抗性鲁棒性的可解释性方法的评估
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00007
A. Chistyakova, M. Cherepnina, K. Arkhipenko, Sergey D. Kuznetsov, Chang-Seok Oh, Sebeom Park
{"title":"Evaluation of interpretability methods for adversarial robustness on real-world datasets","authors":"A. Chistyakova, M. Cherepnina, K. Arkhipenko, Sergey D. Kuznetsov, Chang-Seok Oh, Sebeom Park","doi":"10.1109/ivmem53963.2021.00007","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00007","url":null,"abstract":"Adversarial training is considered the most powerful approach for robustness against attacks on deep neural networks involving adversarial examples. However, recent works have shown that the similar robustness level can be achieved by other means, namely interpretability-based regularization. We evaluate these interpretability-based approaches on real-world ResNet models trained on CIFAR-10 and ImageNet datasets. Our results show that interpretability can marginally improve robustness when combined with adversarial training, however, they bring additional computational complexity making these approaches questionable for such models and datasets.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133673058","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
Legal Documents Links Extraction 法律文件链接摘录
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00018
Diana Rudenko, K. Skorniakov, Y. Nedumov
{"title":"Legal Documents Links Extraction","authors":"Diana Rudenko, K. Skorniakov, Y. Nedumov","doi":"10.1109/ivmem53963.2021.00018","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00018","url":null,"abstract":"The presence of links in a text always causes difficulties in reading. It happens because it is often not easy to follow a text link, what especially comes to legal references. And there are still no solutions published for automate links extraction regarding to Russian legal documents. Therefore, the purpose of this work was to build a method of automatic search, extraction and structure allocation of legal references using a formal grammar. Besides the method we also build a link describing manifest and dataset for evaluation. Moreover, during the work there has been made a research showing how strict are government recommendations to the links writing observed in real life. Evaluation of our method showed that it helps to extract 94% of links with 98% quality.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130327296","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: 0
Electronic catalog and process automatization system of personalised synthesis of lower limb prosthetic modules 下肢假肢模块个性化合成电子目录及过程自动化系统
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00012
E. Fogt, L. Smirnova, A. V. Sinegub
{"title":"Electronic catalog and process automatization system of personalised synthesis of lower limb prosthetic modules","authors":"E. Fogt, L. Smirnova, A. V. Sinegub","doi":"10.1109/ivmem53963.2021.00012","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00012","url":null,"abstract":"In the article described the need to create a system for automating the process of personalized synthesis of modular prostheses of the lower extremities, an approach to its development in the framework of solving the problem of digitalization of the Russian healthcare system. The description of the developed system in the form of a web application is presented. This system is an interactive electronic database that combines information about prosthetic modules widely used in practice, and provides the function of virtual synthesis of the prosthesis, taking into account the individual characteristics and needs of the patient. The result is achieved by filtering the database of prosthetic modules and applying decision-making methods. The positive effects of using the system are: making it easier for the prosthetic technician to make a decision when choosing the components of the prosthesis; improving the quality of prosthetics due to the reasonable choice of prosthetic modules and reducing the risk of errors associated with the human factor; improving the efficiency of interaction between public services involved in providing rehabilitation services to the population.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114573225","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: 0
A dynamic algorithm for source code static analysis 一个动态算法静态分析的源代码
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00016
P. Mezhuev, A. Gerasimov, P. Privalov, V. Butkevich
{"title":"A dynamic algorithm for source code static analysis","authors":"P. Mezhuev, A. Gerasimov, P. Privalov, V. Butkevich","doi":"10.1109/ivmem53963.2021.00016","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00016","url":null,"abstract":"A source code static analysis became an industrial standard for program source code issues early detection. As one of requirements to such kind of analysis is high performance to provide response of automatic code checking tool as early as possible as far as such kind of tools integrates to Continuous testing and Integration systems. In this paper we propose a source code static analysis algorithm for solving performance issue of source code static analysis tool in general way.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124907520","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: 0
Inclusion imaging using single-shot ultrasound and convolutional neural networks 包涵体成像采用单次超声和卷积神经网络
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00020
A. Stankevich, A. Vasyukov, Igor Petrov
{"title":"Inclusion imaging using single-shot ultrasound and convolutional neural networks","authors":"A. Stankevich, A. Vasyukov, Igor Petrov","doi":"10.1109/ivmem53963.2021.00020","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00020","url":null,"abstract":"This paper consider the problem of harder inclusion localization in an elastic media. The imaging method is based on a single-shot ultrasound with a linear array. Discontinuous Galerkin method is used for direct problem modeling and obtaining wave propagation patterns in the media. Two different architectures of convolutional neural networks are used for the inverse problem. The paper provides the numerical results for the quality of the inclusion localization depending on the neural network architecture and the shape of the heterogeneity.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126511989","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: 0
Towards Symbolic Pointers Reasoning in Dynamic Symbolic Execution 动态符号执行中的符号指针推理
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/IVMEM53963.2021.00014
D. Kuts
{"title":"Towards Symbolic Pointers Reasoning in Dynamic Symbolic Execution","authors":"D. Kuts","doi":"10.1109/IVMEM53963.2021.00014","DOIUrl":"https://doi.org/10.1109/IVMEM53963.2021.00014","url":null,"abstract":"Dynamic symbolic execution is a widely used technique for automated software testing, designed for execution paths exploration and program errors detection. A hybrid approach has recently become widespread, when the main goal of symbolic execution is helping fuzzer increase program coverage. The more branches symbolic executor can invert, the more useful it is for fuzzer. A program control flow often depends on memory values, which are obtained by computing address indexes from user input. However, most DSE tools don’t support such dependencies, so they miss some desired program branches.We implement symbolic addresses reasoning on memory reads in our dynamic symbolic execution tool Sydr. Possible memory access regions are determined by either analyzing memory address symbolic expressions, or binary searching with SMT-solver. We propose an enhanced linearization technique to model memory accesses.Different memory modeling methods are compared on the set of programs. Our evaluation shows that symbolic addresses handling allows to discover new symbolic branches and increase the program coverage.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127360343","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: 6
Survey of Open-source Flows for Digital Hardware Design 数字硬件设计的开源流程综述
2021 Ivannikov Memorial Workshop (IVMEM) Pub Date : 2021-09-01 DOI: 10.1109/ivmem53963.2021.00008
M. Chupilko, A. Kamkin, S. Smolov
{"title":"Survey of Open-source Flows for Digital Hardware Design","authors":"M. Chupilko, A. Kamkin, S. Smolov","doi":"10.1109/ivmem53963.2021.00008","DOIUrl":"https://doi.org/10.1109/ivmem53963.2021.00008","url":null,"abstract":"This paper considers open-source tools for the logical-synthesis and place-and-route hardware design stages. Several flows (CADs), including qFlow, OpenLANE, Coriolis, VTR, and SymbiFlow, have been described. For experimental evaluation of these flows, two RISC-V implementations have been used: schoolRISCV and PicoRV32. The results show that open-source flows are capable to produce physical layouts for realistic examples. At the same time, commercial CADs allow generating more effective designs in terms of clock frequency.","PeriodicalId":360766,"journal":{"name":"2021 Ivannikov Memorial Workshop (IVMEM)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123679390","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: 2
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信