Filters








14 Hits in 8.6 sec

Towards Accurate Run-Time Hardware-Assisted Stealthy Malware Detection: A Lightweight, Yet Effective Time Series CNN-Based Approach

Hossein Sayadi, Yifeng Gao, Hosein Mohammadi Makrani, Jessica Lin, Paulo Cesar Costa, Setareh Rafatirad, Houman Homayoun
2021 Cryptography  
Our analysis demonstrates that using state-of-the-art ML-based malware detection methods is not effective in detecting stealthy malware samples since the captured HPC data not only represents malware but  ...  stealthy malware trace at run-time using branch instructions, the most prominent HPC feature.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/cryptography5040028 fatcat:tdgn54ormvf4tidbwzajazjwky

Two Sides of the Same Coin: Boons and Banes of Machine Learning in Hardware Security

Wenye Liu, Chip-Hong Chang, Xueyang Wang, Chen Liu, Jason Fung, Mohammad Ebrahimabadi, Naghmeh Karimi, Xingyu Meng, Kanad Basu
2021 IEEE Journal on Emerging and Selected Topics in Circuits and Systems  
ML schemes have been extensively used to enhance the security and trust of embedded systems like hardware Trojans and malware detection.  ...  We will discuss the possible future research directions, and thereby, sharing a roadmap for the hardware security community in general.  ...  [124] proposed a lightweight customized ML-based malware detection method, where a classifier was trained individually with characteristics of a specific class of malware using only four selected HPCs  ... 
doi:10.1109/jetcas.2021.3084400 fatcat:c4wdkghpo5fwbhvkekaysnahzm

Fog-based Attack Detection Framework for Internet of Things Using Deep Learning

Ahmed Samy, Haining Yu, Hongli Zhang
2020 IEEE Access  
and 99.65% detection accuracy in multi-class classification.  ...  The proposed framework is effective in terms of response time and detection accuracy and can detect several types of cyber-attacks with 99.97% detection rate and 99.96% detection accuracy in binary classification  ...  The deep belief network model, combined with a conventional stochastic gradient descent method, was used for classification.  ... 
doi:10.1109/access.2020.2988854 fatcat:6t34wvczbzaqbgvguinp47u5mi

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

Tanujay Saha, Najwa Aaraj, Neel Ajjarapu, Niraj K. Jha
2021 arXiv   pre-print
The ML methodology achieves an accuracy of 97.4% and enables us to predict these attacks efficiently with an 87.2% reduction in the search space.  ...  This defense mechanism optimizes the cost of security measures based on the sensitivity of the protected resource, thus incentivizing its adoption in real-world CPS/IoT by cybersecurity practitioners.  ...  Another ML-based malware detection method analyzes the hardware performance counters (HPCs) to detect malware execution at run-time [36] .  ... 
arXiv:2101.02780v1 fatcat:6mqftspb7nbijbaupom3ernoqa

NLP Methods in Host-based Intrusion Detection Systems: A Systematic Review and Future Directions [article]

Zarrin Tasnim Sworna, Zahra Mousavi, Muhammad Ali Babar
2022 arXiv   pre-print
The Host-Based Intrusion Detection Systems (HIDS) are widely used for defending against cybersecurity attacks.  ...  We conduct a systematic review of the literature on NLP-based HIDS in order to build a systematized body of knowledge.  ...  text classification) creates a huge potential research horizon to improve the accuracy and reduce the FAR of HIDS.  ... 
arXiv:2201.08066v1 fatcat:t6nsqoj5hnhnhcv4hsugsnau6m

Self-protection of Android systems from inter-component communication attacks

Mahmoud Hammad, Joshua Garcia, Sam Malek
2018 Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering - ASE 2018  
Consequently, to perform feature selection, we used a stochastic gradient descent (SGD) classifier, which is a classifier based on an optimization method for unconstrained optimization problems [226,  ...  In fact, the accuracy of F-Secure, GData, BitDefender, and Emsisoft improves on apps obfuscated using REF.  ...  The experimental evaluations show that RevealDroid achieves an accuracy of 98% in detection of malware and an accuracy of 95% in determination of their families.  ... 
doi:10.1145/3238147.3238207 dblp:conf/kbse/HammadGM18 fatcat:qht4e54ehjfltlht6wjuwzsata

Side-Channel Assisted Malware Classifier with Gradient Descent Correction for Embedded Platforms

Manaar Alam, Debdeep Mukhopadhyay, Sai Praveen Kadiyala, Siew Kei Lam, Thambipillai Srikanthan
unpublished
We employ a gradient-descent based learning mechanism to determine optimal choices for these weights.  ...  We justify through experimental results on an embedded Linux running on an ARM processor that such a side-channel based learning mechanism improves the classification accuracy significantly compared to  ...  We are also grateful to the anonymous reviewers for their insightful comments and suggestions.  ... 
doi:10.29007/5sdj fatcat:iudhpjn7r5hwzn42hsmbvi6xle

D1.1 - State of the Art Analysis

Danilo Ardagna
2021 Zenodo  
The aim of this deliverable is to review the state-of-the-art in techniques used in the development and operation of AI applications in computing continua and the related technologies.  ...  The aim of the AI-SPRINT "Artificial intelligence in Secure PRIvacy-preserving computing coNTinuum" project is to develop a platform composed of design and runtime management tools to seamlessly design  ...  The specific gradient-based algorithms are usually improvements of the well-known stochastic gradient descent (SGD).  ... 
doi:10.5281/zenodo.6372377 fatcat:f6ldfuwivbcltew4smiiwphfty

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

Muhammad Zeeshan Asghar, Mudassar Abbas, Khaula Zeeshan, Pyry Kotilainen, Timo Hämäläinen
2019 Applied Sciences  
Our empirical study presents a framework for cell outage detection based on an autoencoder using simulated data obtained from a SON simulator.  ...  In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON).  ...  Secondly, the computational power, especially HPC and cloud computing, would further provide the platform for the rapid training of deep learning models.  ... 
doi:10.3390/app9152975 fatcat:n7pgi2a4mba6xpo7cwphuw3ivu

International Journal of Computer Science July 2021

IJCSIS Editor
2021 Zenodo  
CALL FOR PAPERS International Journal of Computer Science and Information Security (IJCSIS) January-December 2021 Issues The topics suggested by this issue can be discussed in term of concepts, surveys  ...  See authors guide for manuscript preparation and submission guidelines.  ...  To tackle the optimization in deep learning, several optimization methods and algorithms have been developed, from gradient descent, stochastic gradient descent and its inherited variants, high-derivative  ... 
doi:10.5281/zenodo.5543977 fatcat:vxk2ynl3l5bbpcvpda2lt4qef4

A Survey on Automated Log Analysis for Reliability Engineering [article]

Shilin He, Pinjia He, Zhuangbin Chen, Tianyi Yang, Yuxin Su, Michael R. Lyu
2021 arXiv   pre-print
Based on the discussion of the recent advances, we present several promising future directions toward real-world and next-generation automated log analysis.  ...  To enable effective and efficient usage of modern software logs in reliability engineering, a number of studies have been conducted on automated log analysis.  ...  [118] presented a systematic review on general compression techniques, based on which they investigated the use of compression for log data reduction and the use of semantic knowledge to improve data  ... 
arXiv:2009.07237v2 fatcat:thbtfboglnglld5rr6s2gqhizi

D3.1 – State-of-the-Art and Market Analysis Report

ASSIST-IoT Consortium
2021 Zenodo  
Document with main results of SotA review and stakeholders and market analysis carried out.  ...  The authors also note that deep learning applications most often rely on the stochastic gradient descent (SGD) method for optimization.  ...  This is a popular synchronous algorithm, which utilizes Stochastic Gradient Descent (SGD).  ... 
doi:10.5281/zenodo.6705158 fatcat:xote6pjzubcvxo4aqxxbraooxi

50 Algebra in Computational Complexity (Dagstuhl Seminar 14391) Manindra Agrawal, Valentine Kabanets, Thomas Thierauf, and Christopher Umans 85 Privacy and Security in an Age of Surveillance (Dagstuhl Perspectives Workshop

Maria-Florina Balcan, Bodo Manthey, Heiko Röglin, Tim Roughgarden, Artur D'avila Garcez, Marco Gori, Pascal Hitzler, Luís Lamb, Bart Preneel, Phillip Rogaway, Mark Ryan, Peter (+5 others)
unpublished
Most of the existing algorithms for dictionary learning minimize a non-convex function by heuristics like alternating minimization, gradient descent or their variants.  ...  Nevertheless, usually one obtains a generalized gradient that can be used for data assimilation and more general optimal control.  ...  What metrics should be optimized?  ... 
fatcat:e5wnf6cuhvc3bceegijgut34zm

Schloss Dagstuhl - Jahresbericht / Annual Report 2017

Schloss Dagstuhl-Leibniz-Zentrum Für Informatik
2018
We thank Schloss Dagstuhl for hosting us.  ...  We further thank Tamara Mchedlidze for helping us collecting the contributions and preparing this report. Acknowledgments.  ...  HPC platforms.  ... 
doi:10.4230/2199-1995.2017 fatcat:im34ekmmxnbrtlgjk3os6u53pq