Szilveszter Kovács was born in Hungary in 1964. He received both the M.Sc. (electrical engineering) and the M.Sc. (computer science) degrees from the Technical University of Budapest, Hungary, in 1989 and 1993, respectively. He received Dr.eng. (Ph.D. in engineering) at the University of Miskolc, Hungary, in 1998. From 1989 he is working at the University of Miskolc, since 2005 he is an Associate Professor at the Department of Information Technology. Address: Department of Information Technology University of Miskolc Miskolc-Egyetemvaros Miskolc H-3515 Hungary
A szakértői tudásbázissal bővített fuzzy szabály-interpoláció alapú Q-learning (FRIQ-learning) me... more A szakértői tudásbázissal bővített fuzzy szabály-interpoláció alapú Q-learning (FRIQ-learning) megerősítéses tanulási rendszerben a szakértői által definiált tudásbázis a tanulási folyamat során kiegészül a rendszer által létrehozott fuzzy szabályokkal. A rendszer a tanulási folyamat során hangolja (és optimalizálja) a tudásbázist leíró fuzzy szabályok antecedensét és konzekvensét is, amely következtében előfordulhat olyan eset, hogy több szabály közel kerül egymáshoz. Az egymáshoz közel kerülő szabályok összevonásával (redukálásával) a rendszer tudásbázisának a mérete csökkenthető. A tudásbázis redukálási módszer a szabályok közötti távolságot (és így a szabályközelség mértékét) az antecedens (állapot-akció) dimenzióban határozza meg. Ez azonban problémát okozhat olyan esetekben mikor a szabályok antecedens univerzumokban közelinek számítanak, azonban a konzekvensükben (Q-érték) nagy eltérés mutatkozik, tehát az általuk leírt Q-függvényben meredek lejtő található. Jelen cikk célja szakértői heurisztikával bővített FRIQ-learning tudásbázis redukálási módszerének kiegészítése (finomítása) olyan módon, hogy az a szabályközelség (és egyben a szabálytávolság) meghatározásánál a szabályok konzekvens (Q-érték) dimenzióját is figyelembe vegye.
2018 19th International Carpathian Control Conference (ICCC)
This paper introduces a novel minimally allowed rule-distance determination methodology for the i... more This paper introduces a novel minimally allowed rule-distance determination methodology for the incremental rule-base construction phase of the FRIQ-learning. The FRIQ-learning process starts from an empty Q-function represented by an empty fuzzy rule-base. Then it creates the fuzzy Q-function in an iterative incremental manner by adding new fuzzy rules in cases where the Q-function update seems to be inefficient by tuning the existing rule base. According to the original FRIQ-learning a new rule is inserted if the Q-function update is high, and even the closest existing fuzzy rule is farther than a preset limit. Improper choice of the minimal rule distance limit can lead to unnecessary high number of inserted rules during the initial steps of the iteration. The main goal of this paper is to introduce a new rule-distance limit calculation methodology which can avoid the unnecessary high number of inserted rules in the initial phase of the iteration. For demonstrating the efficiency of the proposed rule-base creation method, the “mountain car” benchmark application example is also discussed briefly in the paper.
2019 IEEE 23rd International Conference on Intelligent Engineering Systems (INES)
Behavior-based system (BBS) is a structure built upon behavior components, behavior coordination ... more Behavior-based system (BBS) is a structure built upon behavior components, behavior coordination and behavior fusion. The goal of this paper is to introduce a declarative language especially designed for supporting embedded behavior- based applications. The suggested language adapts the BBS implementation based on fuzzy rule-based systems, fuzzy rule interpolation (FRI) and fuzzy state machines. This case the description of the BBS as a network of behaviors turns to a network of fuzzy systems. The suggested Fuzzy Behavior Description Language (FBDL), is a declarative language for defining FRI rule-bases and a network of fuzzy systems in a unified framework. According to the suggested concept, the FBDL code is "running", as a parameter configuration, directly on a FRI state machine called "FRI Behavior Engine". In an embedded behavior-based application, the FRI Behavior Engine with the parameter configuration fetched from the FBDL code can directly serve the actions according to the observations and the state of the system.
2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2015
The fuzzy rule interpolation (FRI) and the fuzzy signature methodology was successfully adapted f... more The fuzzy rule interpolation (FRI) and the fuzzy signature methodology was successfully adapted for expressing the building condition. In this paper we extend this concept for estimating the life quality of the built environment, especially of the residential segment. The applied methodology is based on a hierarchical FRI as a straightforward implementation of the fuzzy signature concept. The paper also introduces some application details of a case study related to residential houses located in a historic district of Budapest, Hungary.
Az informatikai halozatot, legyen az otthoni, kisvallalati, vagy akar egy komplett osszetett nagy... more Az informatikai halozatot, legyen az otthoni, kisvallalati, vagy akar egy komplett osszetett nagyhalozat, mindig erik tamadasok. A halozatokban a rendszeradminisztratorok gyakran csalikent hasznalnak specialis eszkozoket (u.n. mezes bodonoket), amelyek segitsegevel a tamadasok felterkepezhetők, a tamadok azonosithatok. Ez lehet egy erre a celra konfiguralt szerver (honeypot), halozat (honeynet) vagy akar telephelyek kozotti osszehangolt rendszer (honeyfarm). Ezek az eszkozok ugy vannak konfiguralva, hogy a tamado a rendszert sebezhetőnek erzekeli, megprobal behatolni, mikozben tenyleges kart nem tud okozni, de nyomot hagy maga utan. Ezekből a nyomokbol informacio szerezhető a tamadorol, es emellett egy behatolas erzekelő rendszer (IDS) tanitasara is hasznosithatok az adatok. Trap on the network Computer networks are frequently targeted by various hostile activities independently of their scale (home, small business, enterprise network). System administrators often employ special too...
Fuzzy Rule Interpolation (FRI) reasoning methods have been introduced to address sparse fuzzy rul... more Fuzzy Rule Interpolation (FRI) reasoning methods have been introduced to address sparse fuzzy rule bases and reduce complexity. The first FRI method was the Koczy and Hirota (KH) proposed "Linear Interpolation". Besides, several conditions and criteria have been suggested for unifying the common requirements FRI methods have to satisfy. One of the most conditions is restricted the fuzzy set of the conclusion must preserve a Piece-Wise Linearity (PWL) if all antecedents and consequents of the fuzzy rules are preserving on PWL sets at α-cut levels. The KH FRI is one of FRI methods which cannot satisfy this condition. Therefore, the goal of this paper is to investigate equations and notations related to PWL property, which is aimed to highlight the problematic properties of the KH FRI method to prove its efficiency with PWL condition. In addition, this paper is focusing on constructing benchmark examples to be a baseline for testing other FRI methods against situations that a...
2016 17th International Carpathian Control Conference (ICCC), 2016
Man-machine interaction, human-robot interaction and robot behavior became an important factor of... more Man-machine interaction, human-robot interaction and robot behavior became an important factor of robotics, since the robotics as a separate research field appeared. Etho robotic is the science, which studies robot habit, which acts as animals or humans. Also it studies human reaction regarding the robot which acts as a dog, ant, or other animals. The paper intends to present a robot behavior model for implementation strategies.
2021 IEEE/SICE International Symposium on System Integration (SII), 2021
The learning phase of the traditional reinforcement learning methods can be started without any p... more The learning phase of the traditional reinforcement learning methods can be started without any preliminary knowledge about the problem needed to be solved. The problem related knowledge-base is built based on the reinforcement signals of the environment during the trial and error style learning phase. If a portion of the a priori knowledge about the problem solution is available and if it could be injected into the initial knowledge of the reinforcement learning system, then the learning performance (and the learning ability of an agent) could be significantly improved. The goal of this paper is to highlight the effect of the external expert knowledge inclusion into the Fuzzy Rule Interpolation based Q-learning (FRIQ-learning) method, by briefly introducing a way for expert knowledge injection into FRIQ-learning and a discussion based on simulated runs of a practical benchmark example. The investigations presented here can aid in the designing of behaviour-based robot control systems, in such cases where the available expert knowledge is not enough by itself to construct a sufficiently working system.
A szamitogepes halozatok megvalositasa soran fontos szempont a kezelhetőseg, a felugyelhetőseg, e... more A szamitogepes halozatok megvalositasa soran fontos szempont a kezelhetőseg, a felugyelhetőseg, es a konfiguralhatosag. A szoftver altal definialt halozatok (Software Defined Networks - SDN) paradigma biztositja ezeket a jellemzőket. Az SDN kulonvalasztja az adatsikot es a vezerlő sikot, mialtal konnyebbe valik a halozat megvalositasa. Az uj megkozelites szerint a fizikai eszkozok csak egyszerű adattovabbitasi feladatot latnak el, mig a vezerles kozpontositasra kerul. Az OpenFlow protokoll alkalmazasaval a halozati eszkozok csak a csomag kuldeset es fogadasat vegzik, az utvonalvalasztas egy felsőbb reteg segitsegevel tortenik. Az SDN koncepcioval jelentős hatekonysag javulas erhető el az erőforras gazdalkodas, az automatizalas es a biztonsag teruleten is. Cikkunkben bemutatjuk az SDN retegeit, funkcioit, es kiterunk a hagyomanyos halozatokkal szembeni előnyokre. Bemutatjuk az SDN altal hasznalt OpenFlow protokollt is. Software defined network – the network of the future In course o...
Computer networks are frequently targeted by various hostile activities independently of their sc... more Computer networks are frequently targeted by various hostile activities independently of their scale (home, small business, enterprise network). System administrators often employ special tools called honeypots as bait in order to discover, understand, and deflect malicious activities and to identify their actors. This task can be done either by a specially configured computer (honeypot), or a group of honeypots on the same network (honeynet), or a centralized system covering several sites (honeyfarm). These tools are configured so that the attacker perceives the system vulnerable; however, it cannot harm it actually. Besides, it also leaves a trace. From the traces of the attacker one can obtain information about the actor and the gained data can be used for the training of an intrusion detection system (IDS).
A szakértői tudásbázissal bővített fuzzy szabály-interpoláció alapú Q-learning (FRIQ-learning) me... more A szakértői tudásbázissal bővített fuzzy szabály-interpoláció alapú Q-learning (FRIQ-learning) megerősítéses tanulási rendszerben a szakértői által definiált tudásbázis a tanulási folyamat során kiegészül a rendszer által létrehozott fuzzy szabályokkal. A rendszer a tanulási folyamat során hangolja (és optimalizálja) a tudásbázist leíró fuzzy szabályok antecedensét és konzekvensét is, amely következtében előfordulhat olyan eset, hogy több szabály közel kerül egymáshoz. Az egymáshoz közel kerülő szabályok összevonásával (redukálásával) a rendszer tudásbázisának a mérete csökkenthető. A tudásbázis redukálási módszer a szabályok közötti távolságot (és így a szabályközelség mértékét) az antecedens (állapot-akció) dimenzióban határozza meg. Ez azonban problémát okozhat olyan esetekben mikor a szabályok antecedens univerzumokban közelinek számítanak, azonban a konzekvensükben (Q-érték) nagy eltérés mutatkozik, tehát az általuk leírt Q-függvényben meredek lejtő található. Jelen cikk célja szakértői heurisztikával bővített FRIQ-learning tudásbázis redukálási módszerének kiegészítése (finomítása) olyan módon, hogy az a szabályközelség (és egyben a szabálytávolság) meghatározásánál a szabályok konzekvens (Q-érték) dimenzióját is figyelembe vegye.
2018 19th International Carpathian Control Conference (ICCC)
This paper introduces a novel minimally allowed rule-distance determination methodology for the i... more This paper introduces a novel minimally allowed rule-distance determination methodology for the incremental rule-base construction phase of the FRIQ-learning. The FRIQ-learning process starts from an empty Q-function represented by an empty fuzzy rule-base. Then it creates the fuzzy Q-function in an iterative incremental manner by adding new fuzzy rules in cases where the Q-function update seems to be inefficient by tuning the existing rule base. According to the original FRIQ-learning a new rule is inserted if the Q-function update is high, and even the closest existing fuzzy rule is farther than a preset limit. Improper choice of the minimal rule distance limit can lead to unnecessary high number of inserted rules during the initial steps of the iteration. The main goal of this paper is to introduce a new rule-distance limit calculation methodology which can avoid the unnecessary high number of inserted rules in the initial phase of the iteration. For demonstrating the efficiency of the proposed rule-base creation method, the “mountain car” benchmark application example is also discussed briefly in the paper.
2019 IEEE 23rd International Conference on Intelligent Engineering Systems (INES)
Behavior-based system (BBS) is a structure built upon behavior components, behavior coordination ... more Behavior-based system (BBS) is a structure built upon behavior components, behavior coordination and behavior fusion. The goal of this paper is to introduce a declarative language especially designed for supporting embedded behavior- based applications. The suggested language adapts the BBS implementation based on fuzzy rule-based systems, fuzzy rule interpolation (FRI) and fuzzy state machines. This case the description of the BBS as a network of behaviors turns to a network of fuzzy systems. The suggested Fuzzy Behavior Description Language (FBDL), is a declarative language for defining FRI rule-bases and a network of fuzzy systems in a unified framework. According to the suggested concept, the FBDL code is "running", as a parameter configuration, directly on a FRI state machine called "FRI Behavior Engine". In an embedded behavior-based application, the FRI Behavior Engine with the parameter configuration fetched from the FBDL code can directly serve the actions according to the observations and the state of the system.
2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2015
The fuzzy rule interpolation (FRI) and the fuzzy signature methodology was successfully adapted f... more The fuzzy rule interpolation (FRI) and the fuzzy signature methodology was successfully adapted for expressing the building condition. In this paper we extend this concept for estimating the life quality of the built environment, especially of the residential segment. The applied methodology is based on a hierarchical FRI as a straightforward implementation of the fuzzy signature concept. The paper also introduces some application details of a case study related to residential houses located in a historic district of Budapest, Hungary.
Az informatikai halozatot, legyen az otthoni, kisvallalati, vagy akar egy komplett osszetett nagy... more Az informatikai halozatot, legyen az otthoni, kisvallalati, vagy akar egy komplett osszetett nagyhalozat, mindig erik tamadasok. A halozatokban a rendszeradminisztratorok gyakran csalikent hasznalnak specialis eszkozoket (u.n. mezes bodonoket), amelyek segitsegevel a tamadasok felterkepezhetők, a tamadok azonosithatok. Ez lehet egy erre a celra konfiguralt szerver (honeypot), halozat (honeynet) vagy akar telephelyek kozotti osszehangolt rendszer (honeyfarm). Ezek az eszkozok ugy vannak konfiguralva, hogy a tamado a rendszert sebezhetőnek erzekeli, megprobal behatolni, mikozben tenyleges kart nem tud okozni, de nyomot hagy maga utan. Ezekből a nyomokbol informacio szerezhető a tamadorol, es emellett egy behatolas erzekelő rendszer (IDS) tanitasara is hasznosithatok az adatok. Trap on the network Computer networks are frequently targeted by various hostile activities independently of their scale (home, small business, enterprise network). System administrators often employ special too...
Fuzzy Rule Interpolation (FRI) reasoning methods have been introduced to address sparse fuzzy rul... more Fuzzy Rule Interpolation (FRI) reasoning methods have been introduced to address sparse fuzzy rule bases and reduce complexity. The first FRI method was the Koczy and Hirota (KH) proposed "Linear Interpolation". Besides, several conditions and criteria have been suggested for unifying the common requirements FRI methods have to satisfy. One of the most conditions is restricted the fuzzy set of the conclusion must preserve a Piece-Wise Linearity (PWL) if all antecedents and consequents of the fuzzy rules are preserving on PWL sets at α-cut levels. The KH FRI is one of FRI methods which cannot satisfy this condition. Therefore, the goal of this paper is to investigate equations and notations related to PWL property, which is aimed to highlight the problematic properties of the KH FRI method to prove its efficiency with PWL condition. In addition, this paper is focusing on constructing benchmark examples to be a baseline for testing other FRI methods against situations that a...
2016 17th International Carpathian Control Conference (ICCC), 2016
Man-machine interaction, human-robot interaction and robot behavior became an important factor of... more Man-machine interaction, human-robot interaction and robot behavior became an important factor of robotics, since the robotics as a separate research field appeared. Etho robotic is the science, which studies robot habit, which acts as animals or humans. Also it studies human reaction regarding the robot which acts as a dog, ant, or other animals. The paper intends to present a robot behavior model for implementation strategies.
2021 IEEE/SICE International Symposium on System Integration (SII), 2021
The learning phase of the traditional reinforcement learning methods can be started without any p... more The learning phase of the traditional reinforcement learning methods can be started without any preliminary knowledge about the problem needed to be solved. The problem related knowledge-base is built based on the reinforcement signals of the environment during the trial and error style learning phase. If a portion of the a priori knowledge about the problem solution is available and if it could be injected into the initial knowledge of the reinforcement learning system, then the learning performance (and the learning ability of an agent) could be significantly improved. The goal of this paper is to highlight the effect of the external expert knowledge inclusion into the Fuzzy Rule Interpolation based Q-learning (FRIQ-learning) method, by briefly introducing a way for expert knowledge injection into FRIQ-learning and a discussion based on simulated runs of a practical benchmark example. The investigations presented here can aid in the designing of behaviour-based robot control systems, in such cases where the available expert knowledge is not enough by itself to construct a sufficiently working system.
A szamitogepes halozatok megvalositasa soran fontos szempont a kezelhetőseg, a felugyelhetőseg, e... more A szamitogepes halozatok megvalositasa soran fontos szempont a kezelhetőseg, a felugyelhetőseg, es a konfiguralhatosag. A szoftver altal definialt halozatok (Software Defined Networks - SDN) paradigma biztositja ezeket a jellemzőket. Az SDN kulonvalasztja az adatsikot es a vezerlő sikot, mialtal konnyebbe valik a halozat megvalositasa. Az uj megkozelites szerint a fizikai eszkozok csak egyszerű adattovabbitasi feladatot latnak el, mig a vezerles kozpontositasra kerul. Az OpenFlow protokoll alkalmazasaval a halozati eszkozok csak a csomag kuldeset es fogadasat vegzik, az utvonalvalasztas egy felsőbb reteg segitsegevel tortenik. Az SDN koncepcioval jelentős hatekonysag javulas erhető el az erőforras gazdalkodas, az automatizalas es a biztonsag teruleten is. Cikkunkben bemutatjuk az SDN retegeit, funkcioit, es kiterunk a hagyomanyos halozatokkal szembeni előnyokre. Bemutatjuk az SDN altal hasznalt OpenFlow protokollt is. Software defined network – the network of the future In course o...
Computer networks are frequently targeted by various hostile activities independently of their sc... more Computer networks are frequently targeted by various hostile activities independently of their scale (home, small business, enterprise network). System administrators often employ special tools called honeypots as bait in order to discover, understand, and deflect malicious activities and to identify their actors. This task can be done either by a specially configured computer (honeypot), or a group of honeypots on the same network (honeynet), or a centralized system covering several sites (honeyfarm). These tools are configured so that the attacker perceives the system vulnerable; however, it cannot harm it actually. Besides, it also leaves a trace. From the traces of the attacker one can obtain information about the actor and the gained data can be used for the training of an intrusion detection system (IDS).
FSTA 2006 8th International Conference on Fuzzy Set Theory and Applications, 2006
Fuzzy rule based systems have been very popular in many engineering applications. However, when g... more Fuzzy rule based systems have been very popular in many engineering applications. However, when generating fuzzy rules from the available information, this may result in a sparse fuzzy rule base. Fuzzy rule interpolation techniques can be used to solve the problems encountered in processing sparse fuzzy rule bases. In most engineering applications, the use of more than one input variable is common. However, studies in multidimensional input spaces using fuzzy rule interpolation techniques (FRIT) are not well addressed in literature to date. Most papers only concentrate in the less important one input variable case. Therefore we aim in this paper to investigate fuzzy rule interpolation techniques w.r.t. how they perform in multidimensional input spaces applications.
AGTEDU 2006: A Magyar Tudomány Ünnepe alkalmából rendezett tudományos konferencia kiadványa, 2006
A fuzzy logikán alapuló rendszerek szabály alapú következtetéssel dolgozva állítják elő az eredmé... more A fuzzy logikán alapuló rendszerek szabály alapú következtetéssel dolgozva állítják elő az eredményt. Működésükre és az általuk számított adatok használhatóságára meghatározó befolyást gyakorol tudásbázisuk szabályrendszere. Amennyiben ez ritkának bizonyul, a klasszikus szabályillesztési elven alapuló következtetési módszerek nem használhatóak. Ilyen esetekben közelítő technikákat alkalmaznak, amelyek a bemenő adatok és az ismert szabályok alapján egy becsült következményt határoznak meg. A szakirodalomban fellelhető módszerek leggyakrabban fuzzy szabályok interpolációjával állítják elő a közelítő eredményt.
Practical task of information reliability and security is the effective intrusion detection and p... more Practical task of information reliability and security is the effective intrusion detection and prevention. Open systems are vulnerable. Having in detail information about system structures, more and more sophisticated network intrusion methods could be easily developed and quickly tested. Intruders are always keeping update information about the current technology and generate new intrusion methods. There are several defense solutions against intrusions. The most common solution is Intrusion Detection System (IDS). For giving a short overview of some IDS methods, this paper applies the commonly available KDD-99 dataset for compare and discuss the IDS performance in case of different intrusion types. In this paper, the IDS performance of the J48, Random Forest, Random Tree, Decision Table, Multi-layer Perceptron (MLP) and Naive Bayes Classifier compared based on the average accuracy rate, precision, false positive and false negative performance in case of DOS, R2L, U2R, and PROBE attacks. Moreover, the focus would be on false alarm values. During the tests, the random forest algorithm produced the highest average of accuracy rate 93.77%, while the Random tree algorithm had the lowest rate 90.57%. The lowest value of false negative was produced by the decision table algorithm.
Fuzzy Rule Interpolation (FRI) offers a convenient way for delivering rule based decisions on con... more Fuzzy Rule Interpolation (FRI) offers a convenient way for delivering rule based decisions on continuous universes avoiding the burden of binary decisions. In contrast with the classical fuzzy systems, FRI decision is also performing well on partially complete rule bases serving the methodologies having incremental rule base creation structure. These features make the FRI methods to be perfect candidate for detecting and preventing different types of attacks in an Intrusion Detection System (IDS) application. This paper aims to introduce a detection approach for slow port scan attacks by adapting the FRI reasoning method. A controlled test-bed environment was also designed and implemented for the purpose of this study. The proposed detection approach was tested and evaluated using different observations. Experimental analysis on a real test-bed environment provides useful insights about the effectiveness of the proposed detection approach. These insights include information regarding the detection approach's efficacy in detecting the port scan attack and in determining its level of severity. In the discussion the efficacy of the proposed detection approach is compared to the SNORT IDS. The results of the comparison showed that the SNORT IDS was unable to detect the slow and very slow port scan attacks whereas the proposed FRI rule based detection approach was able to detect the attacks and generate comprehensive results to further analyze the attack's severity.
Recently, the Internet of Things (IoT) has been used in technology for different aspects to incre... more Recently, the Internet of Things (IoT) has been used in technology for different aspects to increase the efficiency and comfort of human life. Protecting the IoT infrastructure is not a straightforward task. There is an urgent need to handle different attack scenarios within the IoT smart environment. Attackers continuously targeted the modern aspects of technology, and trying abusing these technologies using complex attack scenarios such as Botnet attacks. Botnet attacks considered a serious challenge faces of the IoT smart environment. In this paper, we introduce a novel idea that capable of supporting the detecting of IoT-Botnet attack and in meanwhile to avoid the issues associated with the deficiencies of the knowledge-based representation and the binary decision. This paper aims to introduce a detection approach for the IoT-BotNet attack by using the Fuzzy Rule Interpolation (FRI). The FRI reasoning methods added a benefit to enhance the robustness of fuzzy systems and effectively reduce the system’s complexity. These benefits help the Intrusion Detection System (IDS) to generate more realistic and comprehensive alerts. The proposed approach was applied to an open-source BoT-IoT dataset from the Cyber Range Lab of the center of UNSW Canberra Cyber. The proposed approach was tested, evaluated and obtained a 95.4% detection rate. Moreover, it effectively smooth the boundary between normal and IoT-BotNet traffics because of its fuzzynature, as well as, it had the ability to generate the required IDS alert in case of the deficiencies of the knowledge-based representation.
Uploads
Papers by Szilveszter Kovacs
and comfort of human life. Protecting the IoT infrastructure is not a straightforward task. There is an urgent need to handle
different attack scenarios within the IoT smart environment. Attackers continuously targeted the modern aspects of technology,
and trying abusing these technologies using complex attack scenarios such as Botnet attacks. Botnet attacks considered a
serious challenge faces of the IoT smart environment. In this paper, we introduce a novel idea that capable of supporting the
detecting of IoT-Botnet attack and in meanwhile to avoid the issues associated with the deficiencies of the knowledge-based
representation and the binary decision. This paper aims to introduce a detection approach for the IoT-BotNet attack by using
the Fuzzy Rule Interpolation (FRI). The FRI reasoning methods added a benefit to enhance the robustness of fuzzy systems
and effectively reduce the system’s complexity. These benefits help the Intrusion Detection System (IDS) to generate more
realistic and comprehensive alerts. The proposed approach was applied to an open-source BoT-IoT dataset from the Cyber
Range Lab of the center of UNSW Canberra Cyber. The proposed approach was tested, evaluated and obtained a 95.4%
detection rate. Moreover, it effectively smooth the boundary between normal and IoT-BotNet traffics because of its fuzzynature, as well as, it had the ability to generate the required IDS alert in case of the deficiencies of the knowledge-based
representation.