Customized Machine Learning-Based Hardware-Assisted Malware Detection in Embedded Devices

Sayadi, Hossein; Makrani, Hosein Mohammadi; Randive, Onkar; D, Sai Manoj P; Rafatirad, Setareh; Homayoun, Houman

doi:10.1109/trustcom/bigdatase.2018.00251

Cited by 36 publications

(19 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods analyze the application programming interface (API) call logs to detect malicious behavior. Another ML-based malware detection method analyzes the hardware performance counters (HPCs) to detect malware execution at run-time [36]. A drawback of ML systems that are trained on API call logs, HPCs, and network logs, is that they are only able to detect the types of malware they have been trained on.…”

Section: Related Workmentioning

confidence: 99%

SHARKS: Smart Hacking Approaches for RisK Scanning in Internet-of-Things and Cyber-Physical Systems based on Machine learning

Saha¹,

Aaraj²,

Ajjarapu³

et al. 2021

IEEE Trans. Emerg. Topics Comput.

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

SHARKS: Smart Hacking Approaches for RisK Scanning in Internet-of-Things and Cyber-Physical Systems based on Machine learning

Saha¹,

Aaraj²,

Ajjarapu³

et al. 2021

IEEE Trans. Emerg. Topics Comput.

View full text Add to dashboard Cite

“…f) Increment the iteration count k then return to step 2 if k < Q, Q is the sparsity level [22]. g) The approximation coefficients for the image have nonzero indices at the elements listed in [5,8,18,38].…”

Section: Restricted Isometry Propertymentioning

confidence: 99%

“…Finally, SAR image has a larger dynamic range compared to the optical image. Because of these differences, the SAR needs special techniques for compression that lead the researchers to make excessive efforts to overcome on these issues [7][8][9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real time FPGA implemnation of SAR radar reconstruction system based on adaptive OMP compressive sensing

Ashraf¹,

Khalaf²,

Hassan³

2020

IJEECS

View full text Add to dashboard Cite

<p><span style="font-size: 9pt; font-family: 'Times New Roman', serif;">Synthetic Aperture Radar (SAR) is an imaging system based on the processing of radar echoes. The produced images have a huge amount of data which will be stored onboard or transmitted as a digital signal to the ground station via downlink to be processed. Therefore, some methods of compression on the raw images provides an attractive option for SAR systems design. One of these techniques which used for image reconstruction is the Orthogonal Matching Pursuit (OMP). OMP is an iterative algorithm which need high computational operations. The computational complexity of the iterative algorithms is high due to updating operations of the measurement vector and large number of iterations that are used to reconstruct the images successfully. This paper presents a new adaptive OMP algorithm to overcome this issue by using certain threshold. The new adaptive OMP algorithm is compared with the classical OMP algorithm using the Receiver Operating Characteristic (ROC) curves. The MATLAB simulations show that the new adaptive OMP algorithm improves the probability of detection at lower SNRs, reduce the computational operations as well as the number of required iterations. FPGA implementation of both the classical OMP and the adaptive OMP algorithm are also presented in this paper.</span></p>

show abstract

“…Smart grids are based on connected IoT and embedded devices that communicate with each other in the power network. Thus, improving the functionality of smart grids, smart buildings, and their IoT devices (e.g., energy management) has become a major research concern [1]. According to the infrastructure provided by smart grids, Demand Response (DR) programs introduce active players into the power distribution system.…”

Section: Introductionmentioning

confidence: 99%

Virtual Organization Structure for Agent-Based Local Electricity Trading

2019

View full text Add to dashboard Cite

End-users are more active because of demand response programs and the penetration of distributed energy resources in the bottom-layer of the power systems. This paper presents a virtual organization of agents of the power distribution grid for local energy trade. An iterative algorithm is proposed; it enables interaction between end-users and the Distribution Company (DisCo). Then, the performance of the proposed algorithm is evaluated in a 33-bus distribution network; its effectiveness is measured in terms of its impact on the energy trading scenarios and, thus, of its contribution to the energy management problem. According to the simulation results, although aggregators do not play the role of decision makers in the proposed model, our iterative algorithm is profitable for them.

show abstract

Customized Machine Learning-Based Hardware-Assisted Malware Detection in Embedded Devices

Cited by 36 publications

References 3 publications

SHARKS: Smart Hacking Approaches for RisK Scanning in Internet-of-Things and Cyber-Physical Systems based on Machine learning

SHARKS: Smart Hacking Approaches for RisK Scanning in Internet-of-Things and Cyber-Physical Systems based on Machine learning

Real time FPGA implemnation of SAR radar reconstruction system based on adaptive OMP compressive sensing

Virtual Organization Structure for Agent-Based Local Electricity Trading

Contact Info

Product

Resources

About