Research article Special Issues

Weighted salp swarm algorithm with deep learning-powered cyber-threat detection for robust network security

  • The fast development of the internet of things has been associated with the complex worldwide problem of protecting interconnected devices and networks. The protection of cyber security is becoming increasingly complicated due to the enormous growth in computer connectivity and the number of new applications related to computers. Consequently, emerging intrusion detection systems could execute a potential cyber security function to identify attacks and variations in computer networks. An efficient data-driven intrusion detection system can be generated utilizing artificial intelligence, especially machine learning methods. Deep learning methods offer advanced methodologies for identifying abnormalities in network traffic efficiently. Therefore, this article introduced a weighted salp swarm algorithm with deep learning-powered cyber-threat detection and classification (WSSADL-CTDC) technique for robust network security, with the aim of detecting the presence of cyber threats, keeping networks secure using metaheuristics with deep learning models, and implementing a min-max normalization approach to scale the data into a uniform format to accomplish this. In addition, the WSSADL-CTDC technique applied the shuffled frog leap algorithm (SFLA) to elect an optimum subset of features and applied a hybrid convolutional autoencoder (CAE) model for cyber threat detection and classification. A WSSA-based hyperparameter tuning method can be employed to enhance the detection performance of the CAE model. The simulation results of the WSSADL-CTDC system were examined in the benchmark dataset. The extensive analysis of the accuracy of the results found that the WSSADL-CTDC technique exhibited a better value of 99.13% than comparable methods on different measures.

    Citation: Maha M. Althobaiti, José Escorcia-Gutierrez. Weighted salp swarm algorithm with deep learning-powered cyber-threat detection for robust network security[J]. AIMS Mathematics, 2024, 9(7): 17676-17695. doi: 10.3934/math.2024859

    Related Papers:

    [1] Zainab Alsheekhhussain, Ahmed Gamal Ibrahim, Rabie A. Ramadan . Existence of S-asymptotically ω-periodic solutions for non-instantaneous impulsive semilinear differential equations and inclusions of fractional order 1<α<2. AIMS Mathematics, 2023, 8(1): 76-101. doi: 10.3934/math.2023004
    [2] Dongdong Gao, Daipeng Kuang, Jianli Li . Some results on the existence and stability of impulsive delayed stochastic differential equations with Poisson jumps. AIMS Mathematics, 2023, 8(7): 15269-15284. doi: 10.3934/math.2023780
    [3] Ramkumar Kasinathan, Ravikumar Kasinathan, Dumitru Baleanu, Anguraj Annamalai . Well posedness of second-order impulsive fractional neutral stochastic differential equations. AIMS Mathematics, 2021, 6(9): 9222-9235. doi: 10.3934/math.2021536
    [4] Huanhuan Zhang, Jia Mu . Periodic problem for non-instantaneous impulsive partial differential equations. AIMS Mathematics, 2022, 7(3): 3345-3359. doi: 10.3934/math.2022186
    [5] Ahmed Salem, Kholoud N. Alharbi . Fractional infinite time-delay evolution equations with non-instantaneous impulsive. AIMS Mathematics, 2023, 8(6): 12943-12963. doi: 10.3934/math.2023652
    [6] Mohamed Adel, M. Elsaid Ramadan, Hijaz Ahmad, Thongchai Botmart . Sobolev-type nonlinear Hilfer fractional stochastic differential equations with noninstantaneous impulsive. AIMS Mathematics, 2022, 7(11): 20105-20125. doi: 10.3934/math.20221100
    [7] Marimuthu Mohan Raja, Velusamy Vijayakumar, Anurag Shukla, Kottakkaran Sooppy Nisar, Wedad Albalawi, Abdel-Haleem Abdel-Aty . A new discussion concerning to exact controllability for fractional mixed Volterra-Fredholm integrodifferential equations of order r(1,2) with impulses. AIMS Mathematics, 2023, 8(5): 10802-10821. doi: 10.3934/math.2023548
    [8] Kanagaraj Muthuselvan, Baskar Sundaravadivoo, Kottakkaran Sooppy Nisar, Suliman Alsaeed . Discussion on iterative process of nonlocal controllability exploration for Hilfer neutral impulsive fractional integro-differential equation. AIMS Mathematics, 2023, 8(7): 16846-16863. doi: 10.3934/math.2023861
    [9] M. Manjula, K. Kaliraj, Thongchai Botmart, Kottakkaran Sooppy Nisar, C. Ravichandran . Existence, uniqueness and approximation of nonlocal fractional differential equation of sobolev type with impulses. AIMS Mathematics, 2023, 8(2): 4645-4665. doi: 10.3934/math.2023229
    [10] Dumitru Baleanu, Rabha W. Ibrahim . Optical applications of a generalized fractional integro-differential equation with periodicity. AIMS Mathematics, 2023, 8(5): 11953-11972. doi: 10.3934/math.2023604
  • The fast development of the internet of things has been associated with the complex worldwide problem of protecting interconnected devices and networks. The protection of cyber security is becoming increasingly complicated due to the enormous growth in computer connectivity and the number of new applications related to computers. Consequently, emerging intrusion detection systems could execute a potential cyber security function to identify attacks and variations in computer networks. An efficient data-driven intrusion detection system can be generated utilizing artificial intelligence, especially machine learning methods. Deep learning methods offer advanced methodologies for identifying abnormalities in network traffic efficiently. Therefore, this article introduced a weighted salp swarm algorithm with deep learning-powered cyber-threat detection and classification (WSSADL-CTDC) technique for robust network security, with the aim of detecting the presence of cyber threats, keeping networks secure using metaheuristics with deep learning models, and implementing a min-max normalization approach to scale the data into a uniform format to accomplish this. In addition, the WSSADL-CTDC technique applied the shuffled frog leap algorithm (SFLA) to elect an optimum subset of features and applied a hybrid convolutional autoencoder (CAE) model for cyber threat detection and classification. A WSSA-based hyperparameter tuning method can be employed to enhance the detection performance of the CAE model. The simulation results of the WSSADL-CTDC system were examined in the benchmark dataset. The extensive analysis of the accuracy of the results found that the WSSADL-CTDC technique exhibited a better value of 99.13% than comparable methods on different measures.



    Fractional differential equations rise in many fields, such as biology, physics and engineering. There are many results about the existence of solutions and control problems (see [1,2,3,4,5,6]).

    It is well known that the nonexistence of nonconstant periodic solutions of fractional differential equations was shown in [7,8,11] and the existence of asymptotically periodic solutions was derived in [8,9,10,11]. Thus it gives rise to study the periodic solutions of fractional differential equations with periodic impulses.

    Recently, Fečkan and Wang [12] studied the existence of periodic solutions of fractional ordinary differential equations with impulses periodic condition and obtained many existence and asymptotic stability results for the Caputo's fractional derivative with fixed and varying lower limits. In this paper, we study the Caputo's fractional evolution equations with varying lower limits and we prove the existence of periodic mild solutions to this problem with the case of general periodic impulses as well as small equidistant and shifted impulses. We also study the Caputo's fractional evolution equations with fixed lower limits and small nonlinearities and derive the existence of its periodic mild solutions. The current results extend some results in [12].

    Set ξq(θ)=1qθ11qϖq(θ1q)0, ϖq(θ)=1πn=1(1)n1θnq1Γ(nq+1)n!sin(nπq), θ(0,). Note that ξq(θ) is a probability density function defined on (0,), namely ξq(θ)0, θ(0,) and 0ξq(θ)dθ=1.

    Define T:XX and S:XX given by

    T(t)=0ξq(θ)S(tqθ)dθ,  S(t)=q0θξq(θ)S(tqθ)dθ.

    Lemma 2.1. ([13,Lemmas 3.2,3.3]) The operators T(t) and S(t),t0 have following properties:

    (1) Suppose that supt0S(t)M. For any fixed t0, T() and S() are linear and bounded operators, i.e., for any uX,

    T(t)uMu and S(t)uMΓ(q)u.

    (2) {T(t),t0} and {S(t),t0} are strongly continuous.

    (3) {T(t),t>0} and {S(t),t>0} are compact, if {S(t),t>0} is compact.

    Let N0={0,1,,}. We consider the following impulsive fractional equations

    {cDqtk,tu(t)=Au(t)+f(t,u(t)), q(0,1), t(tk,tk+1), kN0,u(t+k)=u(tk)+Δk(u(tk)), kN,u(0)=u0, (2.1)

    where cDqtk,t denotes the Caputo's fractional time derivative of order q with the lower limit at tk, A:D(A)XX is the generator of a C0-semigroup {S(t),t0} on a Banach space X, f:R×XX satisfies some assumptions. We suppose the following conditions:

    (Ⅰ) f is continuous and T-periodic in t.

    (Ⅱ) There exist constants a>0, bk>0 such that

    {f(t,u)f(t,v)auv, tR, u,vX,uv+Δk(u)Δk(v)bkuv, kN, u,vX.

    (Ⅲ) There exists NN such that T=tN+1,tk+N+1=tk+T and Δk+N+1=Δk for any kN.

    It is well known [3] that (2.1) has a unique solution on R+ if the conditions (Ⅰ) and (Ⅱ) hold. So we can consider the Poincaré mapping

    P(u0)=u(T)+ΔN+1(u(T)).

    By [14,Lemma 2.2] we know that the fixed points of P determine T-periodic mild solutions of (2.1).

    Theorem 2.2. Assume that (I)-(III) hold. Let Ξ:=Nk=0MbkEq(Ma(tk+1tk)q), where Eq is the Mittag-Leffler function (see [3, p.40]), then there holds

    P(u)P(v)Ξuv, u,vX. (2.2)

    If Ξ<1, then (2.1) has a unique T-periodic mild solution, which is also asymptotically stable.

    Proof. By the mild solution of (2.1), we mean that uC((tk,tk+1),X) satisfying

    u(t)=T(ttk)u(t+k)+ttkS(ts)f(s,u(s))ds. (2.3)

    Let u and v be two solutions of (2.3) with u(0)=u0 and v(0)=v0, respectively. By (2.3) and (II), we can derive

    u(t)v(t)T(ttk)(u(t+k)v(t+k))+ttk(ts)q1S(ts)(f(s,u(s)f(s,v(s))dsMu(t+k)v(t+k)+MaΓ(q)ttk(ts)q1f(s,u(s)f(s,v(s))ds. (2.4)

    Applying Gronwall inequality [15, Corollary 2] to (2.4), we derive

    u(t)v(t)Mu(t+k)v(t+k)Eq(Ma(ttk)q), t(tk,tk+1), (2.5)

    which implies

    u(tk+1)v(tk+1)MEq(Ma(tk+1tk)q)u(t+k)v(t+k),k=0,1,,N. (2.6)

    By (2.6) and (Ⅱ), we derive

    P(u0)P(v0)=u(tN+1)v(tN+1)+ΔN+1(u(tN+1))ΔN+1(v(tN+1))bN+1u(tN+1)v(tN+1)(Nk=0MbkEq(Ma(tk+1tk)q))u0v0=Ξu0v0, (2.7)

    which implies that (2.2) is satisfied. Thus P:XX is a contraction if Ξ<1. Using Banach fixed point theorem, we obtain that P has a unique fixed point u0 if Ξ<1. In addition, since

    Pn(u0)Pn(v0)Ξnu0v0, v0X,

    we get that the corresponding periodic mild solution is asymptotically stable.

    We study

    {cDqkhu(t)=Au(t)+f(u(t)), q(0,1), t(kh,(k+1)h), kN0,u(kh+)=u(kh)+ˉΔhq, kN,u(0)=u0, (2.8)

    where h>0, ˉΔX, and f:XX is Lipschitz. We know [3] that under above assumptions, (2.8) has a unique mild solution u(u0,t) on R+, which is continuous in u0X, tR+{kh|kN} and left continuous in t ant impulsive points {kh|kN}. We can consider the Poincaré mapping

    Ph(u0)=u(u0,h+).

    Theorem 2.3. Let w(t) be a solution of following equations

    {w(t)=ˉΔ+1Γ(q+1)f(w(t)), t[0,T],w(0)=u0. (2.9)

    Then there exists a mild solution u(u0,t) of (2.8) on [0,T], satisfying

    u(u0,t)=w(tqq1)+O(hq).

    If w(t) is a stable periodic solution, then there exists a stable invariant curve of Poincaré mapping of (2.8) in a neighborhood of w(t). Note that h is sufficiently small.

    Proof. For any t(kh,(k+1)h),kN0, the mild solution of (2.8) is equivalent to

    u(u0,t)=T(tkh)u(kh+)+tkh(ts)q1S(ts)f(u(u0,s))ds=T(tkh)u(kh+)+tkh0(tkhs)q1S(tkhs)f(u(u(kh+),s))ds. (2.10)

    So

    u((k+1)h+)=T(h)u(kh+)+ˉΔhq+h0(hs)q1S(hs)f(u(u(kh+),s))ds=Ph(u(kh+)), (2.11)

    and

    Ph(u0)=u(u0,h+)=T(h)u0+ˉΔhq+h0(hs)q1S(hs)f(u(u0,s))ds. (2.12)

    Inserting

    u(u0,t)=T(t)u0+hqv(u0,t), t[0,h],

    into (2.10), we obtain

    v(u0,t)=1hqt0(ts)q1S(ts)f(T(t)u0+hqv(u0,t))ds=1hqt0(ts)q1S(ts)f(T(t)u0)ds+1hqt0(ts)q1S(ts)(f(T(t)u0+hqv(u0,t))f(T(t)u0))ds=1hqt0(ts)q1S(ts)f(T(t)u0)ds+O(hq),

    since

    t0(ts)q1S(ts)(f(T(t)u0+hqv(u0,t))f(T(t)u0))dst0(ts)q1S(ts)f(T(t)u0+hqv(u0,t))f(T(t)u0)dsMLlochqtqΓ(q+1)maxt[0,h]{v(u0,t)}h2qMLlocΓ(q+1)maxt[0,h]{v(u0,t)},

    where Lloc is a local Lipschitz constant of f. Thus we get

    u(u0,t)=T(t)u0+t0(ts)q1S(ts)f(T(t)u0)ds+O(h2q), t[0,h], (2.13)

    and (2.12) gives

    Ph(u0)=T(h)u0+ˉΔhq+h0(hs)q1S(hs)f(T(h)u0)ds+O(h2q).

    So (2.11) becomes

    u((k+1)h+)=T(h)u(kh+)+ˉΔhq+(k+1)hkh((k+1)hs)q1S((k+1)hs)f(T(h)u(kh+))ds+O(h2q). (2.14)

    Since T(t) and S(t) are strongly continuous,

    limt0T(t)=I and limt0S(t)=1Γ(q)I. (2.15)

    Thus (2.14) leads to its approximation

    w((k+1)h+)=w(kh+)+ˉΔhq+hqΓ(q+1)f(w(kh+)),

    which is the Euler numerical approximation of

    w(t)=ˉΔ+1Γ(q+1)f(w(t)).

    Note that (2.10) implies

    u(u0,t)T(tkh)u(kh+)=O(hq), t[kh,(k+1)h]. (2.16)

    Applying (2.15), (2.16) and the already known results about Euler approximation method in [16], we obtain the result of Theorem 2.3.

    Corollary 2.4. We can extend (2.8) for periodic impulses of following form

    {cDqkhu(t)=Au(t)+f(u(t)), t(kh,(k+1)h), kN0,u(kh+)=u(kh)+ˉΔkhq, kN,u(0)=u0, (2.17)

    where ˉΔkX satisfy ˉΔk+N+1=ˉΔk for any kN. Then Theorem 2.3 can directly extend to (2.17) with

    {w(t)=N+1k=1ˉΔkN+1+1Γ(q+1)f(w(t)), t[0,T], kN,w(0)=u0 (2.18)

    instead of (2.9).

    Proof. We can consider the Poincaré mapping

    Ph(u0)=u(u0,(N+1)h+),

    with a form of

    Ph=PN+1,hP1,h

    where

    Pk,h(u0)=ˉΔkhq+u(u0,h).

    By (2.13), we can derive

    Pk,h(u0)=ˉΔkhq+u(u0,h)=T(h)u0+ˉΔkhq+h0(hs)q1S(hs)f(T(h)u0)ds+O(h2q).

    Then we get

    Ph(u0)=T(h)u0+N+1k=1ˉΔkhq+(N+1)h0(hs)q1S(hs)f(T(h)u0)ds+O(h2q).

    By (2.15), we obtain that Ph(u0) leads to its approximation

    u0+N+1k=1ˉΔkhq+(N+1)hqΓ(q+1)f(u0). (2.19)

    Moreover, equations

    w(t)=N+1k=1ˉΔkN+1+1Γ(q+1)f(w(t))

    has the Euler numerical approximation

    u0+hq(N+1k=1ˉΔkN+1+1Γ(q+1)f(u0))

    with the step size hq, and its approximation of N+1 iteration is (2.19), the approximation of Ph. Thus Theorem 2.3 can directly extend to (2.17) with (2.18).

    Now we consider following equations with small nonlinearities of the form

    {cDq0u(t)=Au(t)+ϵf(t,u(t)), q(0,1), t(tk,tk+1), kN0,u(t+k)=u(tk)+ϵΔk(u(tk)), kN,u(0)=u0, (3.1)

    where ϵ is a small parameter, cDq0 is the generalized Caputo fractional derivative with lower limit at 0. Then (3.1) has a unique mild solution u(ϵ,t). Give the Poincaré mapping

    P(ϵ,u0)=u(ϵ,T)+ϵΔN+1(u(ϵ,T)).

    Assume that

    (H1) f and Δk are C2-smooth.

    Then P(ϵ,u0) is also C2-smooth. In addition, we have

    u(ϵ,t)=T(t)u0+ϵω(t)+O(ϵ2),

    where ω(t) satisfies

    {cDq0ω(t)=Aω(t)+f(t,T(t)u0), t(tk,tk+1), k=0,1,,N,ω(t+k)=ω(tk)+Δk(T(tk)u0), k=1,2,,N+1,ω(0)=0,

    and

    ω(T)=Nk=1T(Ttk)Δk(T(tk)u0)+T0(Ts)q1S(Ts)f(s,T(s)u0)ds.

    Thus we derive

    {P(ϵ,u0)=u0+M(ϵ,u0)+O(ϵ2)M(ϵ,u0)=(T(T)I)u0+ϵω(T)+ϵΔN+1(T(T)u0). (3.2)

    Theorem 3.1. Suppose that (I), (III) and (H1) hold.

    1). If (T(T)I) has a continuous inverse, i.e. (T(T)I)1 exists and continuous, then (3.1) has a unique T-periodic mild solution located near 0 for any ϵ0 small.

    2). If (T(T)I) is not invertible, we suppose that ker(T(T)I)=[u1,,uk] and X=im(T(T)I)X1 for a closed subspace X1 with dimX1=k. If there is v0[u1,,uk] such that B(0,v0)=0 (see (3.7)) and the k×k-matrix DB(0,v0) is invertible, then (3.1) has a unique T-periodic mild solution located near T(t)v0 for any ϵ0 small.

    3). If rσ(Du0M(ϵ,u0))<0, then the T-periodic mild solution is asymptotically stable. If rσ(Du0M(ϵ,u0))(0,+), then the T-periodic mild solution is unstable.

    Proof. The fixed point u0 of P(ϵ,x0) determines the T-periodic mild solution of (3.1), which is equivalent to

    M(ϵ,u0)+O(ϵ2)=0. (3.3)

    Note that M(0,u0)=(T(T)I)u0. If (T(T)I) has a continuous inverse, then (3.3) can be solved by the implicit function theorem to get its solution u0(ϵ) with u0(0)=0.

    If (T(T)I) is not invertible, then we take a decomposition u0=v+w, v[u1,,uk], take bounded projections Q1:Xim(T(T)I), Q2:XX1, I=Q1+Q2 and decompose (3.3) to

    Q1M(ϵ,v+w)+Q1O(ϵ2)=0, (3.4)

    and

    Q2M(ϵ,v+w)+Q2O(ϵ2)=0. (3.5)

    Now Q1M(0,v+w)=(T(T)I)w, so we can solve by implicit function theorem from (3.4), w=w(ϵ,v) with w(0,v)=0. Inserting this solution into (3.5), we get

    B(ϵ,v)=1ϵ(Q2M(ϵ,v+w)+Q2O(ϵ2))=Q2ω(T)+Q2ΔN+1(T(t)v+w(ϵ,v))+O(ϵ). (3.6)

    So

    B(0,v)=Nk=1Q2T(Ttk)Δk(T(tk)v)+Q2T0(Ts)q1S(Ts)f(s,T(s)v)ds. (3.7)

    Consequently we get, if there is v0[u1,,uk] such that B(0,v0)=0 and the k×k-matrix DB(0,v0) is invertible, then (3.1) has a unique T-periodic mild solution located near T(t)v0 for any ϵ0 small.

    In addition, Du0P(ϵ,u0(ϵ))=I+Du0M(ϵ,u0)+O(ϵ2). Thus we can directly derive the stability and instability results by the arguments in [17].

    In this section, we give an example to demonstrate Theorem 2.2.

    Example 4.1. Consider the following impulsive fractional partial differential equation:

    { cD12tk,tu(t,y)=2y2u(t,y)+sinu(t,y)+cos2πt,  t(tk,tk+1), kN0,  y[0,π], Δk(u(tk,y))=u(t+k,y)u(tk,y)=ξu(tk,y),  kN,  y[0,π], u(t,0)=u(t,π)=0,  t(tk,tk+1),  kN0, u(0,y)=u0(y),  y[0,π], (4.1)

    for ξR, tk=k3. Let X=L2[0,π]. Define the operator A:D(A)XX by Au=d2udy2 with the domain

    D(A)={uXdudy,d2udy2X, u(0)=u(π)=0}.

    Then A is the infinitesimal generator of a C0-semigroup {S(t),t0} on X and S(t)M=1 for any t0. Denote u(,y)=u()(y) and define f:[0,)×XX by

    f(t,u)(y)=sinu(y)+cos2πt.

    Set T=t3=1, tk+3=tk+1, Δk+3=Δk, a=1, bk=|1+ξ|. Obviously, conditions (I)-(III) hold. Note that

    Ξ=2k=0|1+ξ|E12(13)=|1+ξ|3(E12(13))3.

    Letting Ξ<1, we get E12(13)1<ξ<E12(13)1. Now all assumptions of Theorem 2.2 hold. Hence, if E12(13)1<ξ<E12(13)1, (4.1) has a unique 1-periodic mild solution, which is also asymptotically stable.

    This paper deals with the existence and stability of periodic solutions of impulsive fractional evolution equations with the case of varying lower limits and fixed lower limits. Although, Fečkan and Wang [12] prove the existence of periodic solutions of impulsive fractional ordinary differential equations in finite dimensional Euclidean space, we extend some results to impulsive fractional evolution equation on Banach space by involving operator semigroup theory. Our results can be applied to some impulsive fractional partial differential equations and the proposed approach can be extended to study the similar problem for periodic impulsive fractional evolution inclusions.

    The authors are grateful to the referees for their careful reading of the manuscript and valuable comments. This research is supported by the National Natural Science Foundation of China (11661016), Training Object of High Level and Innovative Talents of Guizhou Province ((2016)4006), Major Research Project of Innovative Group in Guizhou Education Department ([2018]012), Foundation of Postgraduate of Guizhou Province (YJSCXJH[2019]031), the Slovak Research and Development Agency under the contract No. APVV-18-0308, and the Slovak Grant Agency VEGA No. 2/0153/16 and No. 1/0078/17.

    All authors declare no conflicts of interest in this paper.



    [1] M. A. Ferrag, O. Friha, L. Maglaras, H. Janicke, L. Shu, Federated deep learning for cyber security in the internet of things: Concepts, applications, and experimental analysis, IEEE Access, 9 (2021), 138509–138542. https://doi.org/10.1109/ACCESS.2021.3118642 doi: 10.1109/ACCESS.2021.3118642
    [2] Y. Li, Y. Zuo, H. Song, Z. Lv, Deep learning in security of internet of things, IEEE Internet Things J., 9 (2022), 22133–22146. https://doi.org/10.1109/JIOT.2021.3106898 doi: 10.1109/JIOT.2021.3106898
    [3] A. Salih, S. T. Zeebaree, S. Ameen, A. Alkhyyat, H. M. Shukur, A survey on the role of artificial intelligence, machine learning and deep learning for cybersecurity attack detection, In: 2021 7th International engineering conference"Research & innovation amid global pandemic" (IEC), IEEE, 2021, 61–66. https://doi.org/10.1109/IEC52205.2021.9476132
    [4] Z. Z. Xian, F. Zhang, Image real-time detection using LSE-Yolo neural network in artificial intelligence-based internet of things for smart cities and smart homes, Wirel. Commun. Mob. Com., 2022 (2022), 2608798. https://doi.org/10.1155/2022/2608798 doi: 10.1155/2022/2608798
    [5] A. D. Raju, I. Y. Abualhaol, R. S. Giagone, Y. Zhou, S. Huang, A survey on cross-architectural IoT malware threat hunting, IEEE Access, 9 (2021), 91686–91709. https://doi.org/10.1109/ACCESS.2021.3091427 doi: 10.1109/ACCESS.2021.3091427
    [6] B. Jothi, M. Pushpalatha, Wils-trs—A novel optimized deep learning based intrusion detection framework for IoT networks, Pers. Ubiquit. Comput., 27 (2023), 1285–1301. https://doi.org/10.1007/s00779-021-01578-5 doi: 10.1007/s00779-021-01578-5
    [7] P. Dixit, S. Silakari, Deep learning algorithms for cybersecurity applications: A technological and status review, Comput. Sci. Rev., 39 (2021), 100317. https://doi.org/10.1016/j.cosrev.2020.100317 doi: 10.1016/j.cosrev.2020.100317
    [8] D. Chen, P. Wawrzynski, Z. Lv, Cyber security in smart cities: A review of deep learning-based applications and case studies, Sustain. Cities Soc., 66 (2021), 102655. https://doi.org/10.1016/j.scs.2020.102655 doi: 10.1016/j.scs.2020.102655
    [9] R. Ahmad, I. Alsmadi, Machine learning approaches to iot security: A systematic literature review, Internet Things, 14 (2021), 100365. https://doi.org/10.1016/j.iot.2021.100365 doi: 10.1016/j.iot.2021.100365
    [10] E. Bout, V. Loscri, A. Gallais, How machine learning changes the nature of cyberattacks on iot networks: A survey, IEEE Commun. Surv. Tutor., 24 (2022), 248–279. https://doi.org/10.1109/COMST.2021.3127267 doi: 10.1109/COMST.2021.3127267
    [11] E. H. Houssein, D. Oliva, N. A. Samee, N. F. Mahmoud, M. M. Emam, Liver cancer algorithm: A novel bio-inspired optimizer, Comput. Biol. Med., 165 (2023), 107389. https://doi.org/10.1016/j.compbiomed.2023.107389 doi: 10.1016/j.compbiomed.2023.107389
    [12] S. Li, H. Chen, M. Wang, A. A. Heidari, S. Mirjalili, Slime mould algorithm: A new method for stochastic optimization, Future Gener. Comp. Syst., 111 (2020), 300–323. https://doi.org/10.1016/j.future.2020.03.055 doi: 10.1016/j.future.2020.03.055
    [13] X. Zhou, Y. Chen, Z. Wu, A. A. Heidari, H. Chen, E. Alabdulkreem, et al., Boosted local dimensional mutation and all-dimensional neighborhood slime mould algorithm for feature selection, Neurocomputing, 551 (2023), 126467. https://doi.org/10.1016/j.neucom.2023.126467 doi: 10.1016/j.neucom.2023.126467
    [14] G. Wang, Moth search algorithm: A bio-inspired metaheuristic algorithm for global optimization problems, Memetic. Comp., 10 (2018), 151–164. https://doi.org/10.1007/s12293-016-0212-3 doi: 10.1007/s12293-016-0212-3
    [15] Y. Yang, H. Chen, A. A. Heidari, A. H. Gandomi, Hunger games search: Visions, conception, implementation, deep analysis, perspectives, and towards performance shifts, Expert Syst. Appl., 177 (2021), 114864. https://doi.org/10.1016/j.eswa.2021.114864 doi: 10.1016/j.eswa.2021.114864
    [16] J. C. Butcher, G. Wanner, Runge-kutta methods: Some historical notes, Appl. Numer. Math., 22 (1996), 113–151. https://doi.org/10.1016/S0168-9274(96)00048-7 doi: 10.1016/S0168-9274(96)00048-7
    [17] J. Tu, H. Chen, M. Wang, A. H. Gandomi, The colony predation algorithm, J. Bionic Eng., 18 (2021), 674–710.
    [18] I. Ahmadianfar, A. A. Heidari, S. Noshadian, H. Chen, A. H. Gandomi, INFO: An efficient optimization algorithm based on weighted mean of vectors, Expert Syst. Appl., 195 (2022), 116516. https://doi.org/10.1016/j.eswa.2022.116516 doi: 10.1016/j.eswa.2022.116516
    [19] A. A. Heidari, S. Mirjalili, H. Faris, I. Aljarah, M. Mafarja, H. Chen, Harris hawks optimization: Algorithm and applications, Future Gener. Comp. Syst., 97 (2019), 849–872. https://doi.org/10.1016/j.future.2019.02.028 doi: 10.1016/j.future.2019.02.028
    [20] H. Su, D. Zhao, A. A. Heidari, L. Liu, X. Zhang, M. Mafarja, et al., RIME: A physics-based optimization, Neurocomputing, 532 (2023), 183–214. https://doi.org/10.1016/j.neucom.2023.02.010 doi: 10.1016/j.neucom.2023.02.010
    [21] Y. Li, D. Zhao, C. Ma, J. Escorcia-Gutierrez, N. O. Aljehane, X. Ye, CDRIME-MTIS: An enhanced rime optimization-driven multi-threshold segmentation for covid-19 X-ray images, Comput. Biol. Med., 169 (2024), 107838. https://doi.org/10.1016/j.compbiomed.2023.107838 doi: 10.1016/j.compbiomed.2023.107838
    [22] A. Yazdinejad, M. Kazemi, R. M. Parizi, A. Dehghantanha, H. Karimipour, An ensemble deep learning model for cyber threat hunting in industrial internet of things, Digit. Commun. Netw., 9 (2023), 101–110. https://doi.org/10.1016/j.dcan.2022.09.008 doi: 10.1016/j.dcan.2022.09.008
    [23] I. A. Khan, N. Moustafa, D. Pi, K. M. Sallam, A. Y. Zomaya, B. Li, A new explainable deep learning framework for cyber threat discovery in industrial iot networks, IEEE Internet Things J., 9 (2022), 11604–11613. https://doi.org/10.1109/JIOT.2021.3130156 doi: 10.1109/JIOT.2021.3130156
    [24] I. Bibi, A. Akhunzada, N. Kumar, Deep AI-powered cyber threat analysis in IIOT, IEEE Internet Things J., 10 (2023), 7749–7760. https://doi.org/10.1109/JIOT.2022.3229722 doi: 10.1109/JIOT.2022.3229722
    [25] S. Das, Y. Manchala, S. K. Rout, S. K. Panda, Deep learning and metaheuristics based cyber threat detection in internet of things enabled smart city environment, 2023. http://dx.doi.org/10.21203/rs.3.rs-3141258/v1
    [26] R. Wei, L. Cai, L. Zhao, A. Yu, D. Meng, DeepHunter: A graph neural network based approach for robust cyber threat hunting, In: Security and privacy in communication networks, Springer, 398 (2021), 3–24. https://doi.org/10.1007/978-3-030-90019-9_1
    [27] A. N. Ndife, Y. Mensin, W. Rakwichian, P. Muneesawang, Cyber-security audit for smart grid networks: An optimized detection technique based on bayesian deep learning, J. Internet Serv. Inf. Secur., 12 (2022), 95–114. https://dx.doi.org/10.22667/JISIS.2022.05.31.095 doi: 10.22667/JISIS.2022.05.31.095
    [28] M. A. Ferrag, D. Hamouda, M. Debbah, L. Maglaras, A. Lakas, Generative adversarial networks-driven cyber threat intelligence detection framework for securing internet of things, In: 2023 19th International conference on distributed computing in smart systems and the internet of things (DCOSS-IoT), IEEE, 2023,196–200. https://doi.org/10.1109/DCOSS-IoT58021.2023.00042
    [29] T. Elangovan, S. Sukumaran, S. Muthumarilakshmi, An efficient recurrent neural network based classification method for cyber threat detection analysis, J. Alebr. Stat., 13 (2022), 5514–5520.
    [30] Y. Zhou, B. Yang, H. Hou, L. Zhang, T. Wang, M. Hu, Continuous leakage-resilient identity-based encryption with tight security, Comput. J., 62 (2019), 1092–1105. https://doi.org/10.1093/comjnl/bxy144 doi: 10.1093/comjnl/bxy144
    [31] J. Xu, S. H. Park, X. Zhang, A bio-inspired motion sensitive model and its application to estimating human gaze positions under classified driving conditions, Neurocomputing, 345 (2019), 23–35. https://doi.org/10.1016/j.neucom.2018.09.093 doi: 10.1016/j.neucom.2018.09.093
    [32] Y. Li, W. G. Cui, H. Huang, Y. Z. Guo, K. Li, T. Tan, Epileptic seizure detection in EEG signals using sparse multiscale radial basis function networks and the fisher vector approach, Knowledge Based Syst., 164 (2019), 96–106. https://doi.org/10.1016/j.knosys.2018.10.029 doi: 10.1016/j.knosys.2018.10.029
    [33] Y. Chen, L. Feng, C. Zheng, T. Zhou, L. Liu, P. Liu, et al., LDANet: Automatic lung parenchyma segmentation from CT images, Comput. Biol. Med., 155 (2023), 106659. https://doi.org/10.1016/j.compbiomed.2023.106659 doi: 10.1016/j.compbiomed.2023.106659
    [34] S. B. Lin, Generalization and expressivity for deep nets, IEEE Trans. Neural Netw. Learn. Syst., 30 (2019), 1392–1406. https://doi.org/10.1109/TNNLS.2018.2868980 doi: 10.1109/TNNLS.2018.2868980
    [35] Q. Pham, B. Mohammadi, R. Moazenzadeh, S. Heddam, R. P. Zolá, A. Sankaran, et al., Prediction of lake water-level fluctuations using adaptive neuro-fuzzy inference system hybridized with metaheuristic optimization algorithms, Appl. Water Sci., 13 (2023), 13. https://doi.org/10.1007/s13201-022-01815-z doi: 10.1007/s13201-022-01815-z
    [36] R. Dash, R. Dash, R. Rautray, An evolutionary framework-based microarray gene selection and classification approach using binary shuffled frog leaping algorithm, J. King Saud Univ. Comput. Inf. Sci., 34 (2022), 880–891. https://doi.org/10.1016/j.jksuci.2019.04.002 doi: 10.1016/j.jksuci.2019.04.002
    [37] M. Mafarja, T. Thaher, M. A. Al-Betar, J. Too, M. A. Awadallah, I. A. Doush, et al., Classification framework for faulty software using enhanced exploratory whale optimizer-based feature selection scheme and random forest ensemble learning, Appl. Intell., 53 (2023), 18715–18757. https://doi.org/10.1007/s10489-022-04427-x doi: 10.1007/s10489-022-04427-x
    [38] P. Bedi, P. Gole, Plant disease detection using hybrid model based on convolutional autoencoder and convolutional neural network, Artif. Intell. Agric., 5 (2021), 90–101. https://doi.org/10.1016/j.aiia.2021.05.002 doi: 10.1016/j.aiia.2021.05.002
    [39] M. A. Syed, R. Syed, Weighted salp swarm algorithm and its applications towards optimal sensor deployment, J. King Saud Univ. Comput. Inf. Sci., 34 (2022), 1285–1295. https://doi.org/10.1016/j.jksuci.2019.07.005 doi: 10.1016/j.jksuci.2019.07.005
    [40] G. D. Singh, V. Tripathi, A. Dumka, R. S. Rathore, M. Bajaj, J. Escorcia-Gutierrez, et al., A novel framework for capacitated sdn controller placement: Balancing latency and reliability with pso algorithm, Alex. Eng. J., 87 (2024), 77–92. https://doi.org/10.1016/j.aej.2023.12.018 doi: 10.1016/j.aej.2023.12.018
    [41] Y. Meidan, M. Bohandana, Y. Mathov, Y. Mirsky, A. Shabtai, D. Breitenbacher, et al., N-BaIoT—Network-based detection of IoT botnet attacks using deep autoencoders, IEEE Pervas. Comput., 17 (2018), 12–22. https://doi.org/10.1109/MPRV.2018.03367731 doi: 10.1109/MPRV.2018.03367731
    [42] F. Alrowais, S. Althahabi, S. S. Alotaibi, A. Mohamed, M. A. Hamza, R. Marzouk, Automated machine learning enabled cyber security threat detection in the internet of things environment, Comput. Syst. Sci. Eng., 45 (2023), 687–700. https://doi.org/10.32604/csse.2023.030188 doi: 10.32604/csse.2023.030188
    [43] N. Savanović, A. Toskovic, A. Petervoic, M. Zivkovic, R. Damaševičius, L. Jovanovic, Intrusion detection in healthcare 4.0 internet of things systems via metaheuristics optimized machine learning, Sustainability, 15 (2023), 12563. https://doi.org/10.3390/su151612563 doi: 10.3390/su151612563
    [44] S. S. Kareem, R. R. Mostafa, F. A. Hashim, H. M. El-Bakry, An effective feature selection model using hybrid metaheuristic algorithms for IoT intrusion detection, Sensors, 22 (2022), 1396. https://doi.org/10.3390/s22041396 doi: 10.3390/s22041396
  • This article has been cited by:

    1. Xinguang Zhang, Lixin Yu, Jiqiang Jiang, Yonghong Wu, Yujun Cui, Gisele Mophou, Solutions for a Singular Hadamard-Type Fractional Differential Equation by the Spectral Construct Analysis, 2020, 2020, 2314-8888, 1, 10.1155/2020/8392397
    2. Xinguang Zhang, Jiqiang Jiang, Lishan Liu, Yonghong Wu, Extremal Solutions for a Class of Tempered Fractional Turbulent Flow Equations in a Porous Medium, 2020, 2020, 1024-123X, 1, 10.1155/2020/2492193
    3. Jingjing Tan, Xinguang Zhang, Lishan Liu, Yonghong Wu, Mostafa M. A. Khater, An Iterative Algorithm for Solving n -Order Fractional Differential Equation with Mixed Integral and Multipoint Boundary Conditions, 2021, 2021, 1099-0526, 1, 10.1155/2021/8898859
    4. Ahmed Alsaedi, Fawziah M. Alotaibi, Bashir Ahmad, Analysis of nonlinear coupled Caputo fractional differential equations with boundary conditions in terms of sum and difference of the governing functions, 2022, 7, 2473-6988, 8314, 10.3934/math.2022463
    5. Lianjing Ni, Liping Wang, Farooq Haq, Islam Nassar, Sarp Erkir, The Effect of Children’s Innovative Education Courses Based on Fractional Differential Equations, 2022, 0, 2444-8656, 10.2478/amns.2022.2.0039
  • Reader Comments
  • © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(993) PDF downloads(58) Cited by(0)

Other Articles By Authors

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog