Pub Date : 2021-01-30DOI: 10.1109/DSC49826.2021.9346263
H. Chien
Considering many Internet of Things (IoT) devices are resource-limited and their identities might disclose sensitive information, highly efficient and anonymous IoT authentication scheme is desirable for these IoT scenarios. In this paper, we propose a new anonymous IoT authentication scheme, using the composite hashing. The merits of this work are four-fold. (1) A new anonymous IoT authentication scheme is proposed; (2) the pre-calculation of pseudonym vectors can tackle Denial-of-Service attacks or unreliable connection issues; (3) the evaluations and analysis demonstrate its excellent performance in terms of computation, communication, and security properties; (4) an instantiation of applying this scheme on a standard IOT protocol like MQTT is described. Its excellent performances make it very attractive for those resource-limited IoT devices with anonymity requirement.
{"title":"Highly Efficient Anonymous IoT Authentication using Composite Hashing","authors":"H. Chien","doi":"10.1109/DSC49826.2021.9346263","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346263","url":null,"abstract":"Considering many Internet of Things (IoT) devices are resource-limited and their identities might disclose sensitive information, highly efficient and anonymous IoT authentication scheme is desirable for these IoT scenarios. In this paper, we propose a new anonymous IoT authentication scheme, using the composite hashing. The merits of this work are four-fold. (1) A new anonymous IoT authentication scheme is proposed; (2) the pre-calculation of pseudonym vectors can tackle Denial-of-Service attacks or unreliable connection issues; (3) the evaluations and analysis demonstrate its excellent performance in terms of computation, communication, and security properties; (4) an instantiation of applying this scheme on a standard IOT protocol like MQTT is described. Its excellent performances make it very attractive for those resource-limited IoT devices with anonymity requirement.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126143390","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}
Pub Date : 2021-01-30DOI: 10.1109/DSC49826.2021.9346230
Sumit Kumar Debnath, K. Sakurai, Kunal Dey, Nibedita Kundu
In the context of privacy preserving protocols, Private Set Intersection (PSI) plays an important role due to their wide applications in recent research community. In general, PSI involves two participants to securely determine the intersection of their respective input sets, not beyond that. These days, in the context of PSI, it is become a common practice to store datasets in the cloud and delegate PSI computation to the cloud on outsourced datasets, similar to secure cloud computing. We call this outsourced PSI as OPSI. In this paper, we design a new construction of OPSI in malicious setting under the Decisional Diffie-Hellman (DDH) assumption without using any random oracle. In particular, our OPSI is the first that incurs linear complexity in malicious environment with not-interactive setup. Further, we employ a random permutation to extend our OPSI to its cardinality variant OPSI-CA. In this case, all the properties remain unchanged except that the adversarial model is semi-honest instead of malicious.
在隐私保护协议的背景下，私有集交集(Private Set Intersection, PSI)由于其广泛的应用而在近年来的研究中扮演着重要的角色。通常，PSI涉及两个参与者来安全地确定他们各自输入集的交集，而不是超出交集。如今，在PSI的背景下，将数据集存储在云中并将PSI计算委托给外包数据集上的云已成为一种常见的做法，类似于安全云计算。我们把这种外包PSI称为OPSI。本文在DDH (Decisional Diffie-Hellman)假设下，设计了一种新的恶意设置下的OPSI结构，不使用任何随机oracle。特别是，我们的OPSI是第一个在非交互式设置的恶意环境中产生线性复杂性的OPSI。此外，我们采用随机排列将我们的OPSI扩展到其基数变体OPSI- ca。在这种情况下，除了对抗性模型是半诚实的而不是恶意的，所有属性都保持不变。
{"title":"Secure Outsourced Private Set Intersection with Linear Complexity","authors":"Sumit Kumar Debnath, K. Sakurai, Kunal Dey, Nibedita Kundu","doi":"10.1109/DSC49826.2021.9346230","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346230","url":null,"abstract":"In the context of privacy preserving protocols, Private Set Intersection (PSI) plays an important role due to their wide applications in recent research community. In general, PSI involves two participants to securely determine the intersection of their respective input sets, not beyond that. These days, in the context of PSI, it is become a common practice to store datasets in the cloud and delegate PSI computation to the cloud on outsourced datasets, similar to secure cloud computing. We call this outsourced PSI as OPSI. In this paper, we design a new construction of OPSI in malicious setting under the Decisional Diffie-Hellman (DDH) assumption without using any random oracle. In particular, our OPSI is the first that incurs linear complexity in malicious environment with not-interactive setup. Further, we employ a random permutation to extend our OPSI to its cardinality variant OPSI-CA. In this case, all the properties remain unchanged except that the adversarial model is semi-honest instead of malicious.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131798075","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}
Pub Date : 2021-01-30DOI: 10.1109/DSC49826.2021.9346258
Sabyasachi Dutta, Arinjita Paul, Rocki H. Ozaki, C. Rangan, K. Sakurai
Storing and processing huge amount of private data is a challenging problem. The problem becomes, in particular, interesting if the user-side storage and computational power is limited. One way to solve the problem of outsourcing private data and maintaining an access control on the storage is proposed by using blockchain technology. However, blockchain technology requires heavy computational power and machinery. In this paper, we propose an approach to store and sell private data with the help of secret sharing. In comparison to blockchain, our methodology is simpler and preserves the privacy of stored data.
{"title":"A Distributed Ledger Management Mechanism for Storing and Selling Private Data","authors":"Sabyasachi Dutta, Arinjita Paul, Rocki H. Ozaki, C. Rangan, K. Sakurai","doi":"10.1109/DSC49826.2021.9346258","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346258","url":null,"abstract":"Storing and processing huge amount of private data is a challenging problem. The problem becomes, in particular, interesting if the user-side storage and computational power is limited. One way to solve the problem of outsourcing private data and maintaining an access control on the storage is proposed by using blockchain technology. However, blockchain technology requires heavy computational power and machinery. In this paper, we propose an approach to store and sell private data with the help of secret sharing. In comparison to blockchain, our methodology is simpler and preserves the privacy of stored data.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132942110","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}
Pub Date : 2021-01-30DOI: 10.1109/DSC49826.2021.9346243
Hao Wang, Chunpeng Ge, Zhe Liu
Blockchain technology enables global mutually trustless participants to reach a consensus on the final state of permissionless distributed and decentralized ledgers. Due to its properties of openness, transparency, irreversibility, and credibility, many systems have been built based on blockchains' structure, such as Bitcoin and Ethereum. With the wide application of blockchains, however, many security problems still exist in blockchains and there have been many malicious attacks against blockchain systems. Although these attacks have been proposed, there lacks a systematic exploration of how these attacks have been conducted and what underlying relationship they have. In this paper, we firstly present and summarize several current attacks on blockchains in three aspects: system deficiency attacks, mining attacks, and network-level attacks. Secondly, we conduct a systematic analysis and evaluation of the possibility of these attacks occurring on major blockchain platforms. Finally, we motivate some research perspectives and challenges for blockchain system security and highlight some potential solutions to these problems.
{"title":"On the Security of Permissionless Blockchain Systems: Challenges and Research Perspective","authors":"Hao Wang, Chunpeng Ge, Zhe Liu","doi":"10.1109/DSC49826.2021.9346243","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346243","url":null,"abstract":"Blockchain technology enables global mutually trustless participants to reach a consensus on the final state of permissionless distributed and decentralized ledgers. Due to its properties of openness, transparency, irreversibility, and credibility, many systems have been built based on blockchains' structure, such as Bitcoin and Ethereum. With the wide application of blockchains, however, many security problems still exist in blockchains and there have been many malicious attacks against blockchain systems. Although these attacks have been proposed, there lacks a systematic exploration of how these attacks have been conducted and what underlying relationship they have. In this paper, we firstly present and summarize several current attacks on blockchains in three aspects: system deficiency attacks, mining attacks, and network-level attacks. Secondly, we conduct a systematic analysis and evaluation of the possibility of these attacks occurring on major blockchain platforms. Finally, we motivate some research perspectives and challenges for blockchain system security and highlight some potential solutions to these problems.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"383 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134211113","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}
Designated verifier signature (DVS) is a variant of digital signature which can designate a verifier to verify signatures. The main difference between message authentication code and DVS is that no shared key is initially set in DVS. In this paper, we propose a new notion, designated verifier signature transformation (DVST), which allows a cloud server to convert a DVS to a multi-designated verifier signature (MDVS) as long as the original verifier provides a token to the server. For more flexible use, the converted signature can support verification with more than threshold number of designated verifiers. Accordingly, a specific security definition is formalized as token unforgability. Our construction is proposed and built from bilinear map with security analysis.
{"title":"Designated Verifier Signature Transformation: A New Framework for One-Time Delegating Verifiability","authors":"Jian-Feng Lin, Jun-Rui Wang, Che-Chia Chang, Yu-Chi Chen","doi":"10.1109/DSC49826.2021.9346244","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346244","url":null,"abstract":"Designated verifier signature (DVS) is a variant of digital signature which can designate a verifier to verify signatures. The main difference between message authentication code and DVS is that no shared key is initially set in DVS. In this paper, we propose a new notion, designated verifier signature transformation (DVST), which allows a cloud server to convert a DVS to a multi-designated verifier signature (MDVS) as long as the original verifier provides a token to the server. For more flexible use, the converted signature can support verification with more than threshold number of designated verifiers. Accordingly, a specific security definition is formalized as token unforgability. Our construction is proposed and built from bilinear map with security analysis.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115627657","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}
Pub Date : 2021-01-30DOI: 10.1109/DSC49826.2021.9346269
Phuc Trinh Dinh, Minho Park
Software-defined networking (SDN) nowadays is extensively being used in a variety of practical settings, provides a new way to manage networks by separating the data plane from its control plane. However, SDN is particularly vulnerable to Distributed Denial of Service (DDoS) attacks because of its centralized control logic. Many studies have been proposed to tackle DDoS attacks in an SDN design using machine-learning-based schemes; however, these feature-based detection schemes are highly resource-intensive and they are unable to perform reliably in such a large-scale SDN network where a massive amount of traffic data is generated from both control and data planes. This can deplete computing resources, degrade network performance, or even shut down the network systems owing to being exhausting resources. To address the above challenges, this paper proposes a big data framework to overcome traditional data processing limitations and to exploit distributed resources effectively for the most compute-intensive tasks such as DDoS attack detection using machine learning techniques, etc. We demonstrate the robustness, scalability, and effectiveness of our framework through practical experiments.
软件定义网络(SDN)通过将数据平面与控制平面分离，提供了一种新的网络管理方式，目前已广泛应用于各种实际环境中。然而，SDN由于其集中控制逻辑，特别容易受到DDoS (Distributed Denial of Service)攻击。已经提出了许多研究，使用基于机器学习的方案来解决SDN设计中的DDoS攻击;然而，这些基于特征的检测方案是高度资源密集型的，无法在如此大规模的SDN网络中可靠地执行，因为SDN网络的控制平面和数据平面都产生了大量的流量数据。这可能会耗尽计算资源，降低网络性能，甚至由于资源耗尽而关闭网络系统。为了解决上述挑战，本文提出了一个大数据框架，以克服传统的数据处理限制，并有效地利用分布式资源进行最计算密集型的任务，如使用机器学习技术进行DDoS攻击检测等。我们通过实际实验证明了我们的框架的健壮性、可伸缩性和有效性。
{"title":"BDF-SDN: A Big Data Framework for DDoS Attack Detection in Large-Scale SDN-Based Cloud","authors":"Phuc Trinh Dinh, Minho Park","doi":"10.1109/DSC49826.2021.9346269","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346269","url":null,"abstract":"Software-defined networking (SDN) nowadays is extensively being used in a variety of practical settings, provides a new way to manage networks by separating the data plane from its control plane. However, SDN is particularly vulnerable to Distributed Denial of Service (DDoS) attacks because of its centralized control logic. Many studies have been proposed to tackle DDoS attacks in an SDN design using machine-learning-based schemes; however, these feature-based detection schemes are highly resource-intensive and they are unable to perform reliably in such a large-scale SDN network where a massive amount of traffic data is generated from both control and data planes. This can deplete computing resources, degrade network performance, or even shut down the network systems owing to being exhausting resources. To address the above challenges, this paper proposes a big data framework to overcome traditional data processing limitations and to exploit distributed resources effectively for the most compute-intensive tasks such as DDoS attack detection using machine learning techniques, etc. We demonstrate the robustness, scalability, and effectiveness of our framework through practical experiments.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116405497","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}
Pub Date : 2021-01-30DOI: 10.1109/DSC49826.2021.9346270
Tieming Geng, L. Njilla, Chin-Tser Huang
The increasing complexity of modern hardware and software platform along with the imperative assurance on stability deems runtime verification of task fulfillment necessary in distributed systems. Distributing the burden of a central verification monitor to individual devices could improve the efficiency. Our previous work shows the possibility of achieving decentralized runtime verification by incorporating some mechanisms of the blockchain technology for locating the accountability when error occurs. However, traditional blockchain technology disallows branching and hence does not support verification of tasks which involves multiway dependencies. In this paper, we introduce a novel approach of smart marker that can be included in a blockchain to enable multiway branching and merging in order to verify the fulfillment of tasks that involve one-to-many and many-to-one dependencies. The design of smart marker satisfies three requirements of recognizability, compatibility, and authenticability. We implement a prototype of the smart marker scheme and analyze its performance.
{"title":"Smart Markers in Smart Contracts: Enabling Multiway Branching and Merging in Blockchain for Decentralized Runtime Verification","authors":"Tieming Geng, L. Njilla, Chin-Tser Huang","doi":"10.1109/DSC49826.2021.9346270","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346270","url":null,"abstract":"The increasing complexity of modern hardware and software platform along with the imperative assurance on stability deems runtime verification of task fulfillment necessary in distributed systems. Distributing the burden of a central verification monitor to individual devices could improve the efficiency. Our previous work shows the possibility of achieving decentralized runtime verification by incorporating some mechanisms of the blockchain technology for locating the accountability when error occurs. However, traditional blockchain technology disallows branching and hence does not support verification of tasks which involves multiway dependencies. In this paper, we introduce a novel approach of smart marker that can be included in a blockchain to enable multiway branching and merging in order to verify the fulfillment of tasks that involve one-to-many and many-to-one dependencies. The design of smart marker satisfies three requirements of recognizability, compatibility, and authenticability. We implement a prototype of the smart marker scheme and analyze its performance.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131610198","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}
Consensus and transaction are the main parts in a blockchain system. However, most cryptographic protocols used in these parts of current blockchains are vulnerable to rapid development of quantum computers. Besides, traditional proof of work (PoW) based consensus protocols such as Bitcoin can not supply memory mining. And the transaction capacity of each block in a blockchain is limited that need to be expanded. In this paper, a new post-quantum poof of work (PoW) consensus algorithm is proposed, which can be used to not only protect the blockchain under the quantum computing attack over existing classical hash based PoW algorithms but also can supply memory mining. Meanwhile, a identity-based post-quantum signature is embed into a transaction process so as to construct lightweight transactions. We thereafter give a detailed description on how the post-quantum lightweight transaction in a blockchain runs. All in all, this work can help to enrich the research on the future post-quantum blockchain (PQB).
{"title":"On the Construction of a Post-Quantum Blockchain","authors":"Jiahui Chen, Wensheng Gan, Muchuang Hu, Chien‐Ming Chen","doi":"10.1109/DSC49826.2021.9346253","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346253","url":null,"abstract":"Consensus and transaction are the main parts in a blockchain system. However, most cryptographic protocols used in these parts of current blockchains are vulnerable to rapid development of quantum computers. Besides, traditional proof of work (PoW) based consensus protocols such as Bitcoin can not supply memory mining. And the transaction capacity of each block in a blockchain is limited that need to be expanded. In this paper, a new post-quantum poof of work (PoW) consensus algorithm is proposed, which can be used to not only protect the blockchain under the quantum computing attack over existing classical hash based PoW algorithms but also can supply memory mining. Meanwhile, a identity-based post-quantum signature is embed into a transaction process so as to construct lightweight transactions. We thereafter give a detailed description on how the post-quantum lightweight transaction in a blockchain runs. All in all, this work can help to enrich the research on the future post-quantum blockchain (PQB).","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128736784","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}
Pub Date : 2020-10-23DOI: 10.1109/DSC49826.2021.9346261
Shiyi Yang, Peilun Wu, Hui Guo
Network intrusion detection (NID) is an essential defense strategy that is used to discover the trace of suspicious user behaviour in large-scale cyberspace, and machine learning (ML), due to its capability of automation and intelligence, has been gradually adopted as a mainstream hunting method in recent years. However, traditional ML based network intrusion detection systems (NIDSs) are not effective to recognize unknown threats and their high detection rate often comes with the cost of high false alarms, which leads to the problem of alarm fatigue. To address the above problems, in this paper, we propose a novel neural network based detection system, DualNet, which is constructed with a general feature extraction stage and a crucial feature learning stage. DualNet can rapidly reuse the spatial-temporal features in accordance with their importance to facilitate the entire learning process and simultaneously mitigate several optimization problems occurred in deep learning (DL). We evaluate the DualNet on two benchmark cyber attack datasets, NSL-KDD and UNSW-NB15. Our experiment shows that DualNet outperforms classical ML based NIDSs and is more effective than existing DL methods for NID in terms of accuracy, detection rate and false alarm rate.
{"title":"DualNet: Locate Then Detect Effective Payload with Deep Attention Network","authors":"Shiyi Yang, Peilun Wu, Hui Guo","doi":"10.1109/DSC49826.2021.9346261","DOIUrl":"https://doi.org/10.1109/DSC49826.2021.9346261","url":null,"abstract":"Network intrusion detection (NID) is an essential defense strategy that is used to discover the trace of suspicious user behaviour in large-scale cyberspace, and machine learning (ML), due to its capability of automation and intelligence, has been gradually adopted as a mainstream hunting method in recent years. However, traditional ML based network intrusion detection systems (NIDSs) are not effective to recognize unknown threats and their high detection rate often comes with the cost of high false alarms, which leads to the problem of alarm fatigue. To address the above problems, in this paper, we propose a novel neural network based detection system, DualNet, which is constructed with a general feature extraction stage and a crucial feature learning stage. DualNet can rapidly reuse the spatial-temporal features in accordance with their importance to facilitate the entire learning process and simultaneously mitigate several optimization problems occurred in deep learning (DL). We evaluate the DualNet on two benchmark cyber attack datasets, NSL-KDD and UNSW-NB15. Our experiment shows that DualNet outperforms classical ML based NIDSs and is more effective than existing DL methods for NID in terms of accuracy, detection rate and false alarm rate.","PeriodicalId":184504,"journal":{"name":"2021 IEEE Conference on Dependable and Secure Computing (DSC)","volume":"7 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114026163","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：