Towards an Energy-Efficient Anomaly-Based Intrusion Detection Engine for Embedded Systems

Viegas, Eduardo K.; Santin, Altair O.; França, André Luiz Pereira de; Jasinski, Ricardo P.; Pedroni, Volnei A.; Oliveira, Luiz S.

doi:10.1109/tc.2016.2560839

Cited by 81 publications

(36 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have conducted experiments on K-nearest neighbor, K-means and neural network codes to show that an important energy can be saved by our approximate CPU in the ML applications in which these codes are widely used. There are several applications that uses K-nearest neighbor [3,26,27], K-means [28,29] and neural networks [30,31] at IoT devices in such a way that classification, clustering In the literature, dynamic accuracy control is also achieved via dynamic voltage scaling (DVS) [24,25]. There is no dedicated approximate operation block in DVS, the selected parts of the processor are forced to behave inexactly by lowering the supply voltage.…”

Section: Iot Applicationsmentioning

confidence: 99%

“…We have conducted experiments on K-nearest neighbor, K-means and neural network codes to show that an important energy can be saved by our approximate CPU in the ML applications in which these codes are widely used. There are several applications that uses K-nearest neighbor [3,26,27], K-means [28,29] and neural networks [30,31] at IoT devices in such a way that classification, clustering and deep learning processes used in IoT systems can also be carried out on the resource-constrained IoT devices, not only on the cloud. So, an approximate CPU can help them to decrease power consumption while calculating intensive computation loads of these algorithms.…”

Section: Iot Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Approximate CPU Design for IoT End-Devices with Learning Capabilities

2020

View full text Add to dashboard Cite

With the rise of Internet of Things (IoT), low-cost resource-constrained devices have to be more capable than traditional embedded systems, which operate on stringent power budgets. In order to add new capabilities such as learning, the power consumption planning has to be revised. Approximate computing is a promising paradigm for reducing power consumption at the expense of inaccuracy introduced to the computations. In this paper, we set forth approximate computing features of a processor that will exist in the next generation low-cost resource-constrained learning IoT devices. Based on these features, we design an approximate IoT processor which benefits from RISC-V ISA. Targeting machine learning applications such as classification and clustering, we have demonstrated that our processor reinforced with approximate operations can save power up to 23% for ASIC implementation while at least 90% top-1 accuracy is achieved on the trained models and test data set.

show abstract

Section: Iot Applicationsmentioning

confidence: 99%

“…We have conducted experiments on K-nearest neighbor, K-means and neural network codes to show that an important energy can be saved by our approximate CPU in the ML applications in which these codes are widely used. There are several applications that uses K-nearest neighbor [3,26,27], K-means [28,29] and neural networks [30,31] at IoT devices in such a way that classification, clustering and deep learning processes used in IoT systems can also be carried out on the resource-constrained IoT devices, not only on the cloud. So, an approximate CPU can help them to decrease power consumption while calculating intensive computation loads of these algorithms.…”

Section: Iot Applicationsmentioning

confidence: 99%

Approximate CPU Design for IoT End-Devices with Learning Capabilities

2020

View full text Add to dashboard Cite

show abstract

“…It will generate oscillation when reconstructing the signal. Although the continuity of soft threshold function is good, shrinkage treatment will affect the approximation degree of reconstructed signal [15,19]. In view of this, a new threshold function is designed on the basis of the hard and soft threshold functions above, and the control factor is introduced to control the shape of the function.…”

Section: 1mentioning

confidence: 99%

An optimization detection algorithm for complex intrusion interference signal in mobile wireless network

Li¹

2019

Discrete &Amp; Continuous Dynamical Systems - S

View full text Add to dashboard Cite

At present, when detecting intrusive interference signals in classified form, the effect of channel denoising is very poor, and the characteristics of the extracted signals are not clear, which can not achieve effective detection of intrusion signals. An algorithm based on wavelet packet frequency hopping estimation for complex network intrusion detection is proposed in this paper. The soft and hard threshold method is used for wavelet coefficient decomposition, threshold processing, and signal reconstruction; according to probability statistics, a new sequence is composed of the spectral amplitude corresponding to the same frequency of each random variable in a random process and the spectrum matrix of intrusion interference signal is formed, so as to extract the characteristic spectrum of intrusion interference signal; by using the energy balance method, Gauss stochastic wavelet characteristics of intrusion signal can be simulated. The results of network intrusion detection are obtained by the Gauss additivity of the high-order cumulants of the network intrusion. The three edge centroid positioning method is applied to achieve the high-precision location of the intrusion point. Experiments show that the algorithm effectively improves the network channel denoising and the feature extraction effect of the intrusion signal, and it is also better than the current algorithm for the detection and location of the interference signals. 2010 Mathematics Subject Classification. 51A40.

show abstract

“…Moreover, Mishra et al presented a study on intrusion detection in cloud environment [6]. Viegas et al proposed a featureselection method to improve the accuracy of IDS and to reduce the energy consumption in embedded system [7].…”

Section: Literature Reviewmentioning

confidence: 99%

Cuckoo Optimisation based Intrusion Detection System for Cloud Computing

Singh¹,

Priyadharshini²,

Leavline³

2018

IJCNIS

View full text Add to dashboard Cite

In the digital era, cloud computing plays a significant role in scalable resource sharing to carry out seamless computing and information sharing. Securing the data, resources, applications and infrastructure of the cloud is a challenging task among the researchers. To secure the cloud, cloud security controls are deployed in the cloud computing environment. The cloud security controls are roughly classified as deterrent controls, preventive controls, detective controls and corrective controls. Among these, detective controls are significantly contributing for cloud security by detecting the possible intrusions to prevent the cloud environment from the possible attacks. This detective control mechanism is established using intrusion detection system (IDS). The detecting accuracy of the IDS greatly depends on the network traffic data that is employed to develop the IDS using machine-learning algorithm. Hence, this paper proposed a cuckoo optimisation-based method to preprocess the network traffic data for improving the detection accuracy of the IDS for cloud security. The performance of the proposed algorithm is compared with the existing algorithms, and it is identified that the proposed algorithm performs better than the other algorithms compared.

show abstract

Towards an Energy-Efficient Anomaly-Based Intrusion Detection Engine for Embedded Systems

Cited by 81 publications

References 38 publications

Approximate CPU Design for IoT End-Devices with Learning Capabilities

Approximate CPU Design for IoT End-Devices with Learning Capabilities

An optimization detection algorithm for complex intrusion interference signal in mobile wireless network

Cuckoo Optimisation based Intrusion Detection System for Cloud Computing

Contact Info

Product

Resources

About