Non-Fungible Tokens (NFT) have gained popularity since 2021, reaching a total market valuation of several billion US dollars, especially in art. This paper highlights the findings of our statistically representative survey of more than 1850 Americans, e.g., 5.7% have already bought an NFT. Unfortunately, that trust has been misplaced on many occasions due to technical and legal issues of most created NFTs. We detail those issues and evaluate them in the case of the most well-known NFT marketplace, i.e., OpenSea.
{"title":"NFT Trust Survey","authors":"Jean-Marc Seigneur, Suzana Moreno","doi":"10.1145/3555776.3577824","DOIUrl":"https://doi.org/10.1145/3555776.3577824","url":null,"abstract":"Non-Fungible Tokens (NFT) have gained popularity since 2021, reaching a total market valuation of several billion US dollars, especially in art. This paper highlights the findings of our statistically representative survey of more than 1850 Americans, e.g., 5.7% have already bought an NFT. Unfortunately, that trust has been misplaced on many occasions due to technical and legal issues of most created NFTs. We detail those issues and evaluate them in the case of the most well-known NFT marketplace, i.e., OpenSea.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"113 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79323879","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}
João Francisco, Miguel E. Coimbra, P. Neto, Felix Freitag, L. Veiga
The model of approximate computing can be used to increase performance or optimize resource usage in stream and graph processing. It can be used to satisfy performance requirements (e.g., throughput, lag) in stream processing by reducing the effort that applications need to process datasets. There are currently multiple stream processing platforms, and most of them do not natively support approximate results. A recent one, Stateful Functions, is an API that uses Flink to enable developers to easily build stream and graph processing applications. It also retains Flink's features like stateful computations, fault-tolerance, scalability, control events and its graph processing library Gelly. Herein we present Approxate, an extension over this platform to support approximate results. It can also support more efficient stream and graph processing by allocating available resources adaptively, driven by user-defined requirements on throughput, lag, and latency. This extension enables flexibility in computational trade-offs such as trading accuracy for performance. The user can choose which metrics should be guaranteed at the cost of others, and/or the accuracy. Approxate incorporates approximate computing (using load shedding) with adaptive accuracy and resource manegement in state-of-the-art stream processing platforms, which are not targeted in other relevant related work. It does not require significant modifications to application code, and minimizes imbalance in data source representation when dropping events.
{"title":"Stateful Adaptive Streams with Approximate Computing and Elastic Scaling","authors":"João Francisco, Miguel E. Coimbra, P. Neto, Felix Freitag, L. Veiga","doi":"10.1145/3555776.3577858","DOIUrl":"https://doi.org/10.1145/3555776.3577858","url":null,"abstract":"The model of approximate computing can be used to increase performance or optimize resource usage in stream and graph processing. It can be used to satisfy performance requirements (e.g., throughput, lag) in stream processing by reducing the effort that applications need to process datasets. There are currently multiple stream processing platforms, and most of them do not natively support approximate results. A recent one, Stateful Functions, is an API that uses Flink to enable developers to easily build stream and graph processing applications. It also retains Flink's features like stateful computations, fault-tolerance, scalability, control events and its graph processing library Gelly. Herein we present Approxate, an extension over this platform to support approximate results. It can also support more efficient stream and graph processing by allocating available resources adaptively, driven by user-defined requirements on throughput, lag, and latency. This extension enables flexibility in computational trade-offs such as trading accuracy for performance. The user can choose which metrics should be guaranteed at the cost of others, and/or the accuracy. Approxate incorporates approximate computing (using load shedding) with adaptive accuracy and resource manegement in state-of-the-art stream processing platforms, which are not targeted in other relevant related work. It does not require significant modifications to application code, and minimizes imbalance in data source representation when dropping events.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"6 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78035215","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}
Indoor Environment Quality (IEQ) is one of the most important goals for smart spaces. Thermal comfort is typically considered the most emphasized factor in IEQ that depends on personalized thermal preference. In this paper, we explore technical challenges to deploying a robot-driven personalized thermal control system that uses a mobile robot for learning user-state-specific preference efficiently. We conduct a few experiments that give a clue to overcome such challenges (i.e. low image recognition) when the system is deployed in a real world. We present future directions to improve robot-driven preference learning from the exploration.
{"title":"Towards Deployment of Mobile Robot driven Preference Learning for User-State-Specific Thermal Control in A Real-World Smart Space","authors":"Geon Kim, Hyunju Kim, Dongman Lee","doi":"10.1145/3555776.3577760","DOIUrl":"https://doi.org/10.1145/3555776.3577760","url":null,"abstract":"Indoor Environment Quality (IEQ) is one of the most important goals for smart spaces. Thermal comfort is typically considered the most emphasized factor in IEQ that depends on personalized thermal preference. In this paper, we explore technical challenges to deploying a robot-driven personalized thermal control system that uses a mobile robot for learning user-state-specific preference efficiently. We conduct a few experiments that give a clue to overcome such challenges (i.e. low image recognition) when the system is deployed in a real world. We present future directions to improve robot-driven preference learning from the exploration.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"75 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86059371","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}
Distributed monitoring is an essential functionality to allow large cluster federations to efficiently schedule applications on a set of available geo-distributed resources. However, periodically reporting the precise status of each available server is both unnecessary to allow accurate scheduling and unscalable when the number of servers grows. This paper proposes Acala, a monitoring framework for geo-distributed cluster federations which aims to provide the management cluster with aggregate information about the entire cluster instead of individual servers. Our evaluations, based on actual deployment under controlled environment in the geo-distributed Grid'5000 testbed, show that Acala reduces the cross-cluster network traffic by up to 99% and the scrape duration by up to 55%.
{"title":"Acala: Aggregate Monitoring for Geo-Distributed Cluster Federations","authors":"Chih-Kai Huang, G. Pierre","doi":"10.1145/3555776.3577716","DOIUrl":"https://doi.org/10.1145/3555776.3577716","url":null,"abstract":"Distributed monitoring is an essential functionality to allow large cluster federations to efficiently schedule applications on a set of available geo-distributed resources. However, periodically reporting the precise status of each available server is both unnecessary to allow accurate scheduling and unscalable when the number of servers grows. This paper proposes Acala, a monitoring framework for geo-distributed cluster federations which aims to provide the management cluster with aggregate information about the entire cluster instead of individual servers. Our evaluations, based on actual deployment under controlled environment in the geo-distributed Grid'5000 testbed, show that Acala reduces the cross-cluster network traffic by up to 99% and the scrape duration by up to 55%.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"126 12","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72444214","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}
Shubham Malaviya, Manish Shukla, Pratik Korat, S. Lodha
Federated learning has emerged as a privacy-preserving technique to learn a machine learning model without requiring users to share their data. Our paper focuses on Federated Semi-Supervised Learning (FSSL) setting wherein users do not have domain expertise or incentives to label data on their device, and the server has access to some labeled data that is annotated by experts. The existing work in FSSL require data augmentation for model training. However, data augmentation is not well defined for prevalent domains like text and graphs. Moreover, non independent and identically distributed (non-i.i.d.) data across users is a significant challenge in federated learning. We propose a generalized framework based on model contrastive learning called FedFAME which does not require data augmentation, thus making it easy to adapt to different domains. Our experiments on image and text datasets show the robustness of FedFAME towards non-i.i.d. data. We have validated our approach by varying data imbalance across users and the number of labeled instances on the server.
{"title":"FedFAME: A Data Augmentation Free Framework based on Model Contrastive Learning for Federated Semi-Supervised Learning","authors":"Shubham Malaviya, Manish Shukla, Pratik Korat, S. Lodha","doi":"10.1145/3555776.3577613","DOIUrl":"https://doi.org/10.1145/3555776.3577613","url":null,"abstract":"Federated learning has emerged as a privacy-preserving technique to learn a machine learning model without requiring users to share their data. Our paper focuses on Federated Semi-Supervised Learning (FSSL) setting wherein users do not have domain expertise or incentives to label data on their device, and the server has access to some labeled data that is annotated by experts. The existing work in FSSL require data augmentation for model training. However, data augmentation is not well defined for prevalent domains like text and graphs. Moreover, non independent and identically distributed (non-i.i.d.) data across users is a significant challenge in federated learning. We propose a generalized framework based on model contrastive learning called FedFAME which does not require data augmentation, thus making it easy to adapt to different domains. Our experiments on image and text datasets show the robustness of FedFAME towards non-i.i.d. data. We have validated our approach by varying data imbalance across users and the number of labeled instances on the server.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"18 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87588849","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}
J. Parra-Ullauri, Xunzheng Zhang, A. Bravalheri, R. Nejabati, D. Simeonidou
Federated learning (FL) is an emerging distributed machine learning technique in which multiple clients collaborate to learn a model under the management of a central server. An FL system depends on a set of initial conditions (i.e., hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters for the central server and clients is a challenging problem. Hyperparameter tuning in FL often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for server and client models, making the tuning process computationally expensive and time-consuming. We propose an implementation based on integrating the FL framework Flower, and the prime optimisation software Optuna for automated and efficient hyperparameter optimisation (HPO) in FL. Through this combination, it is possible to tune hyperparameters in both clients and server online, aiming to find the optimal values at runtime. We introduce the HPO factor to describe the number of rounds that the HPO will take place, and the HPO rate that defines the frequency for updating the hyperparameters and can be used for pruning. The HPO is managed by the FL server which updates clients' hyperparameters, with an HPO rate, using state-of-the-art optimisation algorithms enabled by Optuna. We tested our approach by updating multiple client models simultaneously in popular image recognition datasets which produced promising results compared to baselines.
{"title":"Federated Hyperparameter Optimisation with Flower and Optuna","authors":"J. Parra-Ullauri, Xunzheng Zhang, A. Bravalheri, R. Nejabati, D. Simeonidou","doi":"10.1145/3555776.3577847","DOIUrl":"https://doi.org/10.1145/3555776.3577847","url":null,"abstract":"Federated learning (FL) is an emerging distributed machine learning technique in which multiple clients collaborate to learn a model under the management of a central server. An FL system depends on a set of initial conditions (i.e., hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters for the central server and clients is a challenging problem. Hyperparameter tuning in FL often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for server and client models, making the tuning process computationally expensive and time-consuming. We propose an implementation based on integrating the FL framework Flower, and the prime optimisation software Optuna for automated and efficient hyperparameter optimisation (HPO) in FL. Through this combination, it is possible to tune hyperparameters in both clients and server online, aiming to find the optimal values at runtime. We introduce the HPO factor to describe the number of rounds that the HPO will take place, and the HPO rate that defines the frequency for updating the hyperparameters and can be used for pruning. The HPO is managed by the FL server which updates clients' hyperparameters, with an HPO rate, using state-of-the-art optimisation algorithms enabled by Optuna. We tested our approach by updating multiple client models simultaneously in popular image recognition datasets which produced promising results compared to baselines.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"62 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72646118","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}
The Generic Integral Tunnel Design (GITO) contains generic models for the tunnel control systems of Rijkswaterstaat, part of the Dutch Ministry of Infrastructure and Water Management. A formal verification of these models advances the safety and reliability of GITO derived tunnel control systems. In this paper, the first known large-scale formalisation of tunnel control systems is presented which transforms GITO models to the formal specification language mCRL2. This transformation is applied to two sub-systems of the GITO to analyse the correctness of the supplied models. In this formal analysis, several deficiencies in the specifications and faults in the existing models are revealed and verified solutions are proposed. Some of the presented faults even find their origin in the legally required standards.
{"title":"A formal analysis of Dutch Generic Integral Tunnel Design models","authors":"Kevin H. J. Jilissen, P. Dieleman, J. F. Groote","doi":"10.1145/3555776.3577786","DOIUrl":"https://doi.org/10.1145/3555776.3577786","url":null,"abstract":"The Generic Integral Tunnel Design (GITO) contains generic models for the tunnel control systems of Rijkswaterstaat, part of the Dutch Ministry of Infrastructure and Water Management. A formal verification of these models advances the safety and reliability of GITO derived tunnel control systems. In this paper, the first known large-scale formalisation of tunnel control systems is presented which transforms GITO models to the formal specification language mCRL2. This transformation is applied to two sub-systems of the GITO to analyse the correctness of the supplied models. In this formal analysis, several deficiencies in the specifications and faults in the existing models are revealed and verified solutions are proposed. Some of the presented faults even find their origin in the legally required standards.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"56 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74734020","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}
Ben Crulis, Barthélémy Serres, Cyril de Runz, G. Venturini
Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in size of deep learning models, it is becoming very difficult to consider training and using artificial neural networks on edge devices such as smartphones. Binary neural networks promise to reduce the size of deep neural network models as well as increasing inference speed while decreasing energy consumption and so allow the deployment of more powerful models on edge devices. However, binary neural networks are still proven to be difficult to train using the backpropagation based gradient descent scheme. We propose to adapt to binary neural networks two training algorithms considered as promising alternatives to backpropagation but for continuous neural networks. We provide experimental comparative results for image classification including the backpropagation baseline on the MNIST, Fashion MNIST and CIFAR-10 datasets in both continuous and binary settings. The results demonstrate that binary neural networks can not only be trained using alternative algorithms to backpropagation but can also be shown to lead better performance and a higher tolerance to the presence or absence of batch normalization layers.
{"title":"Are alternatives to backpropagation useful for training Binary Neural Networks? An experimental study in image classification","authors":"Ben Crulis, Barthélémy Serres, Cyril de Runz, G. Venturini","doi":"10.1145/3555776.3577674","DOIUrl":"https://doi.org/10.1145/3555776.3577674","url":null,"abstract":"Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in size of deep learning models, it is becoming very difficult to consider training and using artificial neural networks on edge devices such as smartphones. Binary neural networks promise to reduce the size of deep neural network models as well as increasing inference speed while decreasing energy consumption and so allow the deployment of more powerful models on edge devices. However, binary neural networks are still proven to be difficult to train using the backpropagation based gradient descent scheme. We propose to adapt to binary neural networks two training algorithms considered as promising alternatives to backpropagation but for continuous neural networks. We provide experimental comparative results for image classification including the backpropagation baseline on the MNIST, Fashion MNIST and CIFAR-10 datasets in both continuous and binary settings. The results demonstrate that binary neural networks can not only be trained using alternative algorithms to backpropagation but can also be shown to lead better performance and a higher tolerance to the presence or absence of batch normalization layers.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"35 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77059636","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}
Smart contracts are programs that are executed on the blockchain and can hold, manage and transfer assets in the form of cryptocurrencies. The contract's execution is then performed on-chain and is subject to consensus, i.e. every node on the blockchain network has to run the function calls and keep track of their side-effects including updates to the balances and contract's storage. The notion of gas is introduced in most programmable blockchains, which prevents DoS attacks from malicious parties who might try to slow down the network by performing time-consuming and resource-heavy computations. While the gas idea has largely succeeded in its goal of avoiding DoS attacks, the resulting fees are extremely high. For example, in June-September 2022, on Ethereum alone, there has been an average total gas usage of 2,706.8 ETH ≈ 3,938,749 USD per day. We propose a protocol for alleviating these costs by moving most of the computation off-chain while preserving enough data on-chain to guarantee an implicit consensus about the contract state and ownership of funds in case of dishonest parties. We perform extensive experiments over 3,330 real-world Solidity contracts that were involved in 327,132 transactions in June-September 2022 on Ethereum and show that our approach reduces their gas usage by 40.09 percent, which amounts to a whopping 442,651 USD.
{"title":"Alleviating High Gas Costs by Secure and Trustless Off-chain Execution of Smart Contracts","authors":"Soroush Farokhnia, Amir Kafshdar Goharshady","doi":"10.1145/3555776.3577833","DOIUrl":"https://doi.org/10.1145/3555776.3577833","url":null,"abstract":"Smart contracts are programs that are executed on the blockchain and can hold, manage and transfer assets in the form of cryptocurrencies. The contract's execution is then performed on-chain and is subject to consensus, i.e. every node on the blockchain network has to run the function calls and keep track of their side-effects including updates to the balances and contract's storage. The notion of gas is introduced in most programmable blockchains, which prevents DoS attacks from malicious parties who might try to slow down the network by performing time-consuming and resource-heavy computations. While the gas idea has largely succeeded in its goal of avoiding DoS attacks, the resulting fees are extremely high. For example, in June-September 2022, on Ethereum alone, there has been an average total gas usage of 2,706.8 ETH ≈ 3,938,749 USD per day. We propose a protocol for alleviating these costs by moving most of the computation off-chain while preserving enough data on-chain to guarantee an implicit consensus about the contract state and ownership of funds in case of dishonest parties. We perform extensive experiments over 3,330 real-world Solidity contracts that were involved in 327,132 transactions in June-September 2022 on Ethereum and show that our approach reduces their gas usage by 40.09 percent, which amounts to a whopping 442,651 USD.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"137 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77813297","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}
Mateusz Gniewkowski, H. Maciejewski, T. Surmacz, Wiktor Walentynowicz
In this paper, we show how methods known from Natural Language Processing (NLP) can be used to detect anomalies in HTTP requests and malicious URLs. Most of the current solutions focusing on a similar problem are either rule-based or trained using manually selected features. Modern NLP methods, however, have great potential in capturing a deep understanding of samples and therefore improving the classification results. Other methods, which rely on a similar idea, often ignore the interpretability of the results, which is so important in machine learning. We are trying to fill this gap. In addition, we show to what extent the proposed solutions are resistant to concept drift. In our work, we compare three different vectorization methods: simple BoW, fastText, and the current state-of-the-art language model RoBERTa. The obtained vectors are later used in the classification task. In order to explain our results, we utilize the SHAP method. We evaluate the feasibility of our methods on four different datasets: CSIC2010, UNSW-NB15, MALICIOUSURL, and ISCX-URL2016. The first two are related to HTTP traffic, the other two contain malicious URLs. The results we show are comparable to others or better, and most importantly - interpretable.
{"title":"Sec2vec: Anomaly Detection in HTTP Traffic and Malicious URLs","authors":"Mateusz Gniewkowski, H. Maciejewski, T. Surmacz, Wiktor Walentynowicz","doi":"10.1145/3555776.3577663","DOIUrl":"https://doi.org/10.1145/3555776.3577663","url":null,"abstract":"In this paper, we show how methods known from Natural Language Processing (NLP) can be used to detect anomalies in HTTP requests and malicious URLs. Most of the current solutions focusing on a similar problem are either rule-based or trained using manually selected features. Modern NLP methods, however, have great potential in capturing a deep understanding of samples and therefore improving the classification results. Other methods, which rely on a similar idea, often ignore the interpretability of the results, which is so important in machine learning. We are trying to fill this gap. In addition, we show to what extent the proposed solutions are resistant to concept drift. In our work, we compare three different vectorization methods: simple BoW, fastText, and the current state-of-the-art language model RoBERTa. The obtained vectors are later used in the classification task. In order to explain our results, we utilize the SHAP method. We evaluate the feasibility of our methods on four different datasets: CSIC2010, UNSW-NB15, MALICIOUSURL, and ISCX-URL2016. The first two are related to HTTP traffic, the other two contain malicious URLs. The results we show are comparable to others or better, and most importantly - interpretable.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":"46 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79851654","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：