The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A carta propõe um novo analisador de vulnerabilidade binária para programas executáveis baseado no Modelo Oculto de Markov. Uma biblioteca de instruções de vulnerabilidade (VIL) é construída principalmente pela coleta de quadros binários localizados por análise de dupla precisão. Os programas executáveis são então convertidos em sequências de código estruturadas com o VIL. As sequências de código são essencialmente sensíveis ao contexto, que podem ser modeladas pelo Hidden Markov Model (HMM). Finalmente, o analisador de vulnerabilidades baseado em HMM é construído para reconhecer vulnerabilidades potenciais de programas executáveis. Os resultados experimentais mostram que a abordagem proposta atinge uma taxa de falsos positivos/negativos mais baixa do que os analisadores estáticos mais recentes.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hao BAI, Chang-zhen HU, Gang ZHANG, Xiao-chuan JING, Ning LI, "Binary Oriented Vulnerability Analyzer Based on Hidden Markov Model" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 12, pp. 3410-3413, December 2010, doi: 10.1587/transinf.E93.D.3410.
Abstract: The letter proposes a novel binary vulnerability analyzer for executable programs that is based on the Hidden Markov Model. A vulnerability instruction library (VIL) is primarily constructed by collecting binary frames located by double precision analysis. Executable programs are then converted into structurized code sequences with the VIL. The code sequences are essentially context-sensitive, which can be modeled by Hidden Markov Model (HMM). Finally, the HMM based vulnerability analyzer is built to recognize potential vulnerabilities of executable programs. Experimental results show the proposed approach achieves lower false positive/negative rate than latest static analyzers.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.3410/_p
Copiar
@ARTICLE{e93-d_12_3410,
author={Hao BAI, Chang-zhen HU, Gang ZHANG, Xiao-chuan JING, Ning LI, },
journal={IEICE TRANSACTIONS on Information},
title={Binary Oriented Vulnerability Analyzer Based on Hidden Markov Model},
year={2010},
volume={E93-D},
number={12},
pages={3410-3413},
abstract={The letter proposes a novel binary vulnerability analyzer for executable programs that is based on the Hidden Markov Model. A vulnerability instruction library (VIL) is primarily constructed by collecting binary frames located by double precision analysis. Executable programs are then converted into structurized code sequences with the VIL. The code sequences are essentially context-sensitive, which can be modeled by Hidden Markov Model (HMM). Finally, the HMM based vulnerability analyzer is built to recognize potential vulnerabilities of executable programs. Experimental results show the proposed approach achieves lower false positive/negative rate than latest static analyzers.},
keywords={},
doi={10.1587/transinf.E93.D.3410},
ISSN={1745-1361},
month={December},}
Copiar
TY - JOUR
TI - Binary Oriented Vulnerability Analyzer Based on Hidden Markov Model
T2 - IEICE TRANSACTIONS on Information
SP - 3410
EP - 3413
AU - Hao BAI
AU - Chang-zhen HU
AU - Gang ZHANG
AU - Xiao-chuan JING
AU - Ning LI
PY - 2010
DO - 10.1587/transinf.E93.D.3410
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2010
AB - The letter proposes a novel binary vulnerability analyzer for executable programs that is based on the Hidden Markov Model. A vulnerability instruction library (VIL) is primarily constructed by collecting binary frames located by double precision analysis. Executable programs are then converted into structurized code sequences with the VIL. The code sequences are essentially context-sensitive, which can be modeled by Hidden Markov Model (HMM). Finally, the HMM based vulnerability analyzer is built to recognize potential vulnerabilities of executable programs. Experimental results show the proposed approach achieves lower false positive/negative rate than latest static analyzers.
ER -