A Probabilistic Approach to Source Code Authorship Identification

Kothari, Jay; Shevertalov, M.; Stehle, Edward; Mancoridis, Spiros

doi:10.1109/itng.2007.17

Cited by 34 publications

(35 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to natural languages, authorship attribution for source code is a much younger field. Early works include Spafford and Weeber [23], Pellen [19], Kothari et al [16], and Frantzeskou et al [10]. Recently, Caliskan-Islam et al [5] improved the state-of-the-art by using a combination of syntactic, lexical, and layout features and achieved higher accuracy over a much larger group of programmers than previous works.…”

Section: Related Workmentioning

confidence: 99%

Recognizing and Imitating Programmer Style: Adversaries in Program Authorship Attribution

Simko

Zettlemoyer

Kohno

2018

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

Source code attribution classifiers have recently become powerful. We consider the possibility that an adversary could craft code with the intention of causing a misclassification, i.e., creating a forgery of another author's programming style in order to hide the forger's own identity or blame the other author. We find that it is possible for a non-expert adversary to defeat such a system. In order to inform the design of adversarially resistant source code attribution classifiers, we conduct two studies with C/C++ programmers to explore the potential tactics and capabilities both of such adversaries and, conversely, of human analysts doing source code authorship attribution. Through the quantitative and qualitative analysis of these studies, we (1) evaluate a state-of-the-art machine classifier against forgeries, (2) evaluate programmers as human analysts/forgery detectors, and (3) compile a set of modifications made to create forgeries. Based on our analyses, we then suggest features that future source code attribution systems might incorporate in order to be adversarially resistant.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognizing and Imitating Programmer Style: Adversaries in Program Authorship Attribution

Simko

Zettlemoyer

Kohno

2018

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

show abstract

“…In [15], the feature extraction technique extracted 170 style-based features including, but not limited to, the number of blank lines, the average sentence length, and the total number of function words. When dealing with source code there are less stylometric features and more lexical features to focus on [21]. In this case an N-Gram based feature extraction technique may be more suitable since this approach is able to capture a trace of style, lexical information, punctuation and capitalization [19].…”

Section: B Author Identificationmentioning

confidence: 99%

Genetic & Evolutionary Feature Selection for Author Identification of HTML Associated with Malware

Williams¹,

Carter²,

Campbell³

et al. 2014

IJMLC

View full text Add to dashboard Cite

Abstract-Malicious software, also known as malware, is a huge problem that costs consumers billions of dollars each year. To solve this problem, a significant amount of research has been dedicated towards detecting malware. In this paper, we introduce a genetic and evolutionary feature selection technique for the identification of HTML code associated with malware. We believe that there may be an association between malware and the HTML code that it is embedded in. Our results show that this technique outperforms previous techniques in terms of recognition accuracy as well as the total number of features needed for recognition.

show abstract

“…This problem is made more difficult by the fact that a different set of metrics may have better performance when considering different groups of authors and therefore needs to be recalculated for each sample set. Kothari et al [13] used entropy filtering to select optimal metrics. Lange et al [14] used a genetic algorithm to achieve similar results.…”

Section: Related Workmentioning

confidence: 99%

“…Previous work by Kothari et al [13] examined source code as a text document and identified certain software developer peculiarities that persisted across different projects. Those styles were used to determine the authorship of disputed source code.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the Use of Discretized Source Code Metrics for Author Identification

Shevertalov

Kothari

Stehle

et al. 2009

2009 1st International Symposium on Search Based Software Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

A Probabilistic Approach to Source Code Authorship Identification

Abstract: There exists a need for tools to help identify the authorship of source code. This includes situations in which the

Cited by 34 publications

References 8 publications

Recognizing and Imitating Programmer Style: Adversaries in Program Authorship Attribution

Recognizing and Imitating Programmer Style: Adversaries in Program Authorship Attribution

Genetic & Evolutionary Feature Selection for Author Identification of HTML Associated with Malware

On the Use of Discretized Source Code Metrics for Author Identification

Contact Info

Product

Resources

About