Anshuman Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anshuman Singh has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Arun Lakhotia
University of Louisiana at Lafayette, Lafayette, LA, USA
5 shared publicationsAndrew Walenstein
University of Louisiana at Lafayette, Lafayette, LA, USA
3 shared publicationsSumi Singh
3 shared publications- Aleardo Manacero
UNESP
2 shared publications - Arun Lakhotia
University of Louisiana at Lafayette
2 shared publications Davidson R. Boccardo
Inmetro—National Institute of Metrology, Quality and Technology
2 shared publications
Latest Publications
- Open Access
- 20 October 2014
- Published by Mathematical Sciences Publishers in Involve, a Journal of Mathematics
- Vol. 7 (6) , 751-767
Zero-inflated Poisson (ZIP) distribution: parameter estimation and applications to model data from natural calamities
This work deals with estimation of parameters of a zero-inflated Poisson (ZIP) distribution as well as using it to model some natural calamities' data. First, we compare the maximum likelihood estimators (MLEs) and the method of moments estimators (MMEs) in terms of standardized bias (SBias) and standardized mean squared error (SMSE). We then proceed to show how datasets from some recent natural disasters can be modeled by the ZIP distribution.
- 20 October 2014
- Published by Mathematical Sciences Publishers in Involve, a Journal of Mathematics
- Vol. 7 (6) , 751-767
Open AccessZero-inflated Poisson (ZIP) distribution: parameter estimation and applications to model data from natural calamities
This work deals with estimation of parameters of a zero-inflated Poisson (ZIP) distribution as well as using it to model some natural calamities' data. First, we compare the maximum likelihood estimators (MLEs) and the method of moments estimators (MMEs) in terms of standardized bias (SBias) and standardized mean squared error (SMSE). We then proceed to show how datasets from some recent natural disasters can be modeled by the ZIP distribution.
- 5 March 2013
- Published by Springer Nature in Journal of Computer Virology and Hacking Techniques
- Vol. 9 (3) , 109-123
VILO: a rapid learning nearest-neighbor classifier for malware triage
- 5 March 2013
- Published by Springer Nature in Journal of Computer Virology and Hacking Techniques
- Vol. 9 (3) , 109-123
VILO: a rapid learning nearest-neighbor classifier for malware triage
- Open Access
- 19 October 2012
- Published by Association for Computing Machinery (ACM)
- p. 81-92
Tracking concept drift in malware families
- 19 October 2012
- Published by Association for Computing Machinery (ACM)
- p. 81-92
Open AccessTracking concept drift in malware families
- 1 January 2012
- Published by Springer Nature
- p. 384-395
Deployable Classifiers for Malware Detection
- Open Access
- 21 October 2011
- Published by Association for Computing Machinery (ACM)
- p. 113-114
On deployable adversarial classification models
- 21 October 2011
- Published by Association for Computing Machinery (ACM)
- p. 113-114
Open AccessOn deployable adversarial classification models
- 1 October 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Game-theoretic design of an information exchange model for detecting packed malware
Packing, a method used by the `good guys' to protect their software from reverse engineering, is also used by the `bad guys' to hide malicious code from being detected by anti-virus (AV) scanners. The AV industry is developing a mechanism to blacklist the software vendors that pack malicious applications, instead of the current practice of blacklisting the packers that are used for packing malicious applications. This will require packer developers to introduce `taggants' in the packed executable and share taggant information in an industry wide information exchange. The idea is similar to the effort of requiring special chemicals to aid in the detection and identification of explosives. In the software context, it is expected that a packer vendor will introduce some secure watermark or signature that can identify the author of a packed binary, and hence help with the detection of malware. For a packer vendor to take on the extra work, which may cost him some customers, the AV industry may need to provide some incentive. However, since a packer vendor is an independent company, likely residing in a different legal jurisdiction, the AV industry cannot verify whether the packer vendor is indeed abiding by the terms of the incentive, and not selling a non-taggant version to malware authors through another channel. We use a game-theoretic modeling approach called the “principal-agent problem” to model the interaction between the AV industry and a packer vendor and give a method of computing the optimal incentive for packer vendors to tag and abide by the terms of the incentive.
- 1 October 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Game-theoretic design of an information exchange model for detecting packed malware
Packing, a method used by the `good guys' to protect their software from reverse engineering, is also used by the `bad guys' to hide malicious code from being detected by anti-virus (AV) scanners. The AV industry is developing a mechanism to blacklist the software vendors that pack malicious applications, instead of the current practice of blacklisting the packers that are used for packing malicious applications. This will require packer developers to introduce `taggants' in the packed executable and share taggant information in an industry wide information exchange. The idea is similar to the effort of requiring special chemicals to aid in the detection and identification of explosives. In the software context, it is expected that a packer vendor will introduce some secure watermark or signature that can identify the author of a packed binary, and hence help with the detection of malware. For a packer vendor to take on the extra work, which may cost him some customers, the AV industry may need to provide some incentive. However, since a packer vendor is an independent company, likely residing in a different legal jurisdiction, the AV industry cannot verify whether the packer vendor is indeed abiding by the terms of the incentive, and not selling a non-taggant version to malware authors through another channel. We use a game-theoretic modeling approach called the “principal-agent problem” to model the interaction between the AV industry and a packer vendor and give a method of computing the optimal incentive for packer vendors to tag and abide by the terms of the incentive.
- 1 September 2010
- Published by Springer Nature in Higher-Order and Symbolic Computation
- Vol. 23 (3) , 275-313
Context-sensitive analysis without calling-context
- 1 September 2010
- Published by Springer Nature in Higher-Order and Symbolic Computation
- Vol. 23 (3) , 275-313
Context-sensitive analysis without calling-context
- Open Access
- 18 January 2010
- Published by Association for Computing Machinery (ACM)
- p. 131-140
Context-sensitive analysis of obfuscated x86 executables
A method for context-sensitive analysis of binaries that may have obfuscated procedure call and return operations is presented. Such binaries may use operators to directly manipulate stack instead of using native call and ret instructions to achieve equivalent behavior. Since definition of context-sensitivity and algorithms for context-sensitive analysis have thus far been based on the specific semantics associated to procedure call and return operations, classic interprocedural analyses cannot be used reliably for analyzing programs in which these operations cannot be discerned. A new notion of context-sensitivity is introduced that is based on the state of the stack at any instruction. While changes in `calling'-context are associated with transfer of control, and hence can be reasoned in terms of paths in an interprocedural control flow graph (ICFG), the same is not true of changes in 'stack'-context. An abstract interpretation based framework is developed to reason about stack-contexts and to derive analogues of call-strings based methods for the context-sensitive analysis using stack-context. The method presented is used to create a context-sensitive version of Venable et al.'s algorithm for detecting obfuscated calls. Experimental results show that the context-sensitive version of the algorithm generates more precise results and is also computationally more efficient than its context-insensitive counterpart.
- 18 January 2010
- Published by Association for Computing Machinery (ACM)
- p. 131-140
Open AccessContext-sensitive analysis of obfuscated x86 executables
A method for context-sensitive analysis of binaries that may have obfuscated procedure call and return operations is presented. Such binaries may use operators to directly manipulate stack instead of using native call and ret instructions to achieve equivalent behavior. Since definition of context-sensitivity and algorithms for context-sensitive analysis have thus far been based on the specific semantics associated to procedure call and return operations, classic interprocedural analyses cannot be used reliably for analyzing programs in which these operations cannot be discerned. A new notion of context-sensitivity is introduced that is based on the state of the stack at any instruction. While changes in `calling'-context are associated with transfer of control, and hence can be reasoned in terms of paths in an interprocedural control flow graph (ICFG), the same is not true of changes in 'stack'-context. An abstract interpretation based framework is developed to reason about stack-contexts and to derive analogues of call-strings based methods for the context-sensitive analysis using stack-context. The method presented is used to create a context-sensitive version of Venable et al.'s algorithm for detecting obfuscated calls. Experimental results show that the context-sensitive version of the algorithm generates more precise results and is also computationally more efficient than its context-insensitive counterpart.