Filters








4,502 Hits in 6.6 sec

Revisiting Binary Code Similarity Analysis using Interpretable Feature Engineering and Lessons Learned [article]

Dongkwan Kim, Eunsoo Kim, Sang Kil Cha, Sooel Son, Yongdae Kim
2021 arXiv   pre-print
Binary code similarity analysis (BCSA) is widely used for diverse security applications such as plagiarism detection, software license violation detection, and vulnerability discovery.  ...  Specifically, we conduct the first systematic study on the basic features used in BCSA by leveraging interpretable feature engineering on a large-scale benchmark.  ...  This mark in the Code and Dataset columns indicates that only a part of them is available.  ... 
arXiv:2011.10749v2 fatcat:xrwqcyimd5esfivr6zyl6dkljq

Driven by Beliefs: Understanding Challenges Physical Science Teachers Face When Integrating Engineering and Physics

Emily A Dare, Joshua A Ellis, Gillian H Roehrig
2014 Journal of Pre-College Engineering Education Research  
Interviews and surveys further revealed the beliefs of these teachers when considering integrating engineering into physics lessons.  ...  While teachers identified both physics and engineering goals for their students, they realized that their students learned more about how to be an engineer.  ...  Acknowledgments This work was funded through the Region 11 Mathematics and Science Teacher Partnership (http://www. region11mathandscience.org/).  ... 
doi:10.7771/2157-9288.1098 fatcat:63qeh2bzbza2ndpwolrawxpiuy

Book reports

2005 Computers and Mathematics with Applications  
Binary Erasure Decoding. 3.9. Modifications to Linear Codes. 3.10. Best Known Linear Block Codes. 3.11. Exercises. 3.12. References. 4. Cyclic Codes,Rings,and Polynomials. 4.1. Introduction. 4.2.  ...  A Direct Formulation for Sparse PCA Using Semidefinite Programming. Comparing Beliefs, Surveys, and Random Walks. The power of feature clustering: An application to object detection.  ... 
doi:10.1016/j.camwa.2005.10.001 fatcat:smjkjmzbkfdbvezerczxaktjfy

Explaining and Measuring Functionalities of Malware Detectors [article]

Wei Wang, Ruoxi Sun, Tian Dong, Shaofeng Li, Minhui Xue, Gareth Tyson, Haojin Zhu
2022 arXiv   pre-print
(i.e., transferability) depends on the overlap of features with large AMM values between the different detectors; and (iii) AMM values effectively measure the importance of features and explain the ability  ...  We find that (i) commercial antivirus engines are vulnerable to AMM-guided manipulated samples; (ii) the ability of a manipulated malware generated using one detector to evade detection by another detector  ...  Revisiting AMM with Improved Detectors We next seek to build on the lessons learnt above, to expand our attack.  ... 
arXiv:2111.10085v2 fatcat:d2rtufif7rdxrbawbhpbwsbpva

Challenges with applying vulnerability prediction models

Patrick Morrison, Kim Herzig, Brendan Murphy, Laurie Williams
2015 Proceedings of the 2015 Symposium and Bootcamp on the Science of Security - HotSoS '15  
However, binaries often exceed 1 million lines of code, too large to practically inspect, and engineers expressed preference for source file level predictions.  ...  We reproduced binarylevel prediction precision (~0.75) and recall (~0.2).  ...  The Tools for Software Engineers team provided significant support, especially Jacek Czerwonka, Michaela Greiler, and John Smyth.  ... 
doi:10.1145/2746194.2746198 dblp:conf/hotsos/MorrisonHMW15 fatcat:5l2rkrknyjg4bc2ctjeinhv36e

ADOxx Modelling Method Conceptualization Environment

Nesat Efendioglu, Robert Woitsch, Wilfrid Utz, Damiano Falcioni
2017 Advances in Science, Technology and Engineering Systems  
a toolbox and lessons learned with the aim to support the engineering of a modelling method.  ...  "The proposed approach is illustrated and validated within use cases from three different EU-funded research projects in the fields of (1) Industry 4.0, (2) e-learning and (3) cloud computing.  ...  Based on these lessons learned, UML [12] has been identified as a starting point.  ... 
doi:10.25046/aj020317 fatcat:hc52uopfrrbvhjhiiaqy2jjdha

Lessons From Deep Neural Networks for Studying the Coding Principles of Biological Neural Networks

Hyojin Bae, Sang Jeong Kim, Chang-Eop Kim
2021 Frontiers in Systems Neuroscience  
and biological neural networks from the perspective of machine learning can be an effective strategy for understanding the coding principles of the brain.  ...  This study aims to not only highlight the importance of careful assumptions and interpretations regarding the neural response to stimulus features but also suggest that the comparative study between deep  ...  However, depending on the research subject and target, researchers may be able to use DNNs with other inductive biases and customize the analysis, structure, and learning of the model.  ... 
doi:10.3389/fnsys.2020.615129 pmid:33519390 pmcid:PMC7843526 fatcat:4rvgny3irnhuxn6qha3t66e5h4

Software penetration testing

B. Arkin, S. Stender, G. McGraw
2005 IEEE Security and Privacy  
lessons to be learned and propagated back  ...  the identified vulnerabilities and any Such tools are often data-driven tests Dataflow diagrams, models, and similar vulnerability in the code base.  ... 
doi:10.1109/msp.2005.23 fatcat:gstkpop3mnfr3nsqrtkrb2fkqi

Concept lattices: A representation space to structure software variability

R. AL-msie'deen, M. Huchard, A.-D. Seriai, C. Urtado, S. Vauttier, A. Al-Khlifat
2014 2014 5th International Conference on Information and Communication Systems (ICICS)  
Comparing theoretically the merging of feature models and what can be learned in the concept structure would really be interesting.  ...  INTRODUCTION Studying variability in domain and software is a key issue of product line engineering.  ... 
doi:10.1109/iacs.2014.6841949 fatcat:i5q2o6r7ffhypai6ikyemdqhzi

Survey of Protocol Reverse Engineering Algorithms: Decomposition of Tools for Static Traffic Analysis

Stephan Kleber, Lisa Maile, Frank Kargl
2018 IEEE Communications Surveys and Tutorials  
We dissect each tool to discern the individual mechanisms and the algorithms on which they are based, then categorize and contrast the mechanisms and algorithms used in static traffic trace analysis to  ...  In this survey, we collect tools presented by prior research in the field of protocol reverse engineering by static traffic trace analysis.  ...  This discussion is intended to provide lessons learned from the application of the methods.  ... 
doi:10.1109/comst.2018.2867544 fatcat:grthgszpq5hflfpaehv4uts6hu

Machine Learning-Based Routing and Wavelength Assignment in Software-Defined Optical Networks

Ignacio Martin, Sebastian Troia, Jose Alberto Hernandez, Alberto Rodriguez, Francesco Musumeci, Guido Maier, Rodolfo Alvizu, Oscar Gonzalez de Dios
2019 IEEE Transactions on Network and Service Management  
Lasso regularization is used due to its well-known performance over binary feature-sets.  ...  The DeepSign approach [82] relies on a Deep Learning system to generate malware signatures from binary application features using an autoencoder network architecture.  ... 
doi:10.1109/tnsm.2019.2927867 fatcat:or3lhqdqbnas3cztwkqr5ykhhq

Meaning and mining: the impact of implicit assumptions in data mining for the humanities

D. Sculley, B. M. Pasanek
2008 Literary and Linguistic Computing  
This article makes explicit some of the foundational assumptions of machine learning methods, and presents a series of experiments as a case study and object lesson in the potential pitfalls in the use  ...  As the use of data mining and machine learning methods in the humanities becomes more common, it will be increasingly important to examine implicit biases, assumptions, and limitations these methods bring  ...  What is the feature space that will be used, and what similarity measure will be used to determine what the 'most similar' pair of examples is at any given step?  ... 
doi:10.1093/llc/fqn019 fatcat:zo2fl64ecvb5bkrsxhhluz3zae

A Law School Course in Applied Legal Analytics and AI

Kevin Ashley, Jaromir Savelka, Matthias Grabmair
2021 Law in context (Bundoora, Vic.)  
We draw some salient comparisons between the 2019 and 2020 versions of the course and report what worked well and what did not, the students' reactions, and lessons learned for future offerings of the  ...  use and evaluate them, and law faculties face the question of how to teach law students the required skills and knowledge to do so.  ...  implementation, and lessons learned.  ... 
doi:10.26826/law-in-context.v37i1.125 fatcat:hogoo644pbfkhdbd5sjubqcckq

Practical Machine Learning for Cloud Intrusion Detection: Challenges and the Way Forward [article]

Ram Shankar Siva Kumar, Andrew Wicker, Matt Swann
2017 arXiv   pre-print
In this paper, we describe the framework, challenges, and open questions surrounding the successful operationalization of machine learning based security detections in a cloud environment and provide some  ...  Operationalizing machine learning based security detections is extremely challenging, especially in a continuously evolving cloud environment.  ...  ACKNOWLEDGMENTS We would like to thank Bryan Smith, Eugene Bobukh, Asghar Dehghani, Anisha Mazumder, Haijun Zhai, and Bin Xu for their valuable comments and members of Identity Driven Machine Learning  ... 
arXiv:1709.07095v1 fatcat:pit6mskwnncfjhaoqf5nmswna4

The Effectiveness of Supervised Machine Learning Algorithms in Predicting Software Refactoring [article]

Maurício Aniche, Erick Maziero, Rafael Durelli, Vinicius Durelli
2020 arXiv   pre-print
More specifically, we train six different machine learning algorithms (i.e., Logistic Regression, Naive Bayes, Support Vector Machine, Decision Trees, Random Forest, and Neural Network) with a dataset  ...  In this paper, we investigate the effectiveness of machine learning algorithms in predicting software refactorings.  ...  Alfredo Goldman (University of São Paulo), Diogo Pina (University of São Paulo), and Matheus Flauzino (Federal University of Lavras) for their feedback on the early steps of this work.  ... 
arXiv:2001.03338v3 fatcat:bpjr2xl6uvdetl42f2du6isg5u
« Previous Showing results 1 — 15 out of 4,502 results