Authorship Attribution for Social Media Forensics

Rocha, Anderson; Scheirer, Walter J.; Forstall, Christopher W.; Cavalcante, Thiago; Theóphilo, Antônio; Shen, Bingyu; Carvalho, Ariadne; Stamatatos, Efstathios

doi:10.1109/tifs.2016.2603960

Cited by 193 publications

(128 citation statements)

References 122 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…Not surprisingly, even just a few short sentences can carry a great deal of information that a human analyst can use for identification, but that information goes beyond the style of the writing. Additional techniques that are capable of exploiting specific domain information are needed; the work of [18] suggests that contextual analysis and tolerance to uncertainty are especially needed for the identification of individuals in social media forensics.…”

Section: Related Workmentioning

confidence: 99%

First Steps towards Data-driven Adversarial Deduplication

Paredes¹,

Simari²,

Martínez³

et al. 2018

Preprint

View full text Add to dashboard Cite

Abstract:In traditional databases, the entity resolution problem (which is also known as deduplication), refers to the task of mapping multiple manifestations of virtual objects to its corresponding real-world entity. When addressing this problem, in both theory and practice, it is widely assumed that such sets of virtual object appear as the result of clerical errors, transliterations, missing or updated attributes, abbreviations, and so forth. In this paper, we address this problem under the assumption that this situation is caused by malicious actors operating in domains in which they do not wish to be identified, such as hacker forums and markets in which the participants are motivated to remain semi-anonymous (though they wish to keep their true identities secret, they find it useful for customers to identify their products and services). We are therefore in the presence of a different, even more challenging problem that we refer to as adversarial deduplication. In this paper, we study this problem via examples that arise from real-world data on malicious hacker forums and markets arising from collaborations with a cyber threat intelligence company focusing on understanding this kind of behavior. We argue that it is very difficult-if not impossible-to find ground truth data on which to build solutions to this problem, and develop a set of preliminary experiments based on training machine learning classifiers that leverage text analysis to detect potential cases of duplicate entities. Our results are encouraging as a first step towards building tools that human analysts can use to enhance their capabilities towards fighting cyber threats.

show abstract

Section: Related Workmentioning

confidence: 99%

First Steps towards Data-driven Adversarial Deduplication

Paredes¹,

Simari²,

Martínez³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Not surprisingly, even just a few short sentences can carry a great deal of information that a human analyst can use for identification, but that information goes beyond the style of the writing. Additional techniques that are capable of exploiting specific domain information are needed; the work of [23] suggests that contextual analysis and tolerance to uncertainty are especially needed for the identification of individuals in social media forensics- [24], on the other hand, also incorporates non-verbal behavior to aid user identification.…”

Section: Related Workmentioning

confidence: 99%

First Steps towards Data-driven Adversarial Deduplication

Paredes¹,

Simari²,

Martínez³

et al. 2018

Preprint

View full text Add to dashboard Cite

Abstract:In traditional databases, the entity resolution problem (which is also known as deduplication), refers to the task of mapping multiple manifestations of virtual objects to its corresponding real-world entity. When addressing this problem, in both theory and practice, it is widely assumed that such sets of virtual objects appear as the result of clerical errors, transliterations, missing or updated attributes, abbreviations, and so forth. In this paper, we address this problem under the assumption that this situation is caused by malicious actors operating in domains in which they do not wish to be identified, such as hacker forums and markets in which the participants are motivated to remain semi-anonymous (though they wish to keep their true identities secret, they find it useful for customers to identify their products and services). We are therefore in the presence of a different, even more challenging problem that we refer to as adversarial deduplication. In this paper, we study this problem via examples that arise from real-world data on malicious hacker forums and markets arising from collaborations with a cyber threat intelligence company focusing on understanding this kind of behavior. We argue that it is very difficult-if not impossible-to find ground truth data on which to build solutions to this problem, and develop a set of preliminary experiments based on training machine learning classifiers that leverage text analysis to detect potential cases of duplicate entities. Our results are encouraging as a first step towards building tools that human analysts can use to enhance their capabilities towards fighting cyber threats.

show abstract

“…In their work they studied two models, the writerdependent and writer-independent. Rocha et al (2016) wrote a review about authorship attribution for social media forensics. They collected data from Twitter and used 50 authors' tweets.…”

Section: Related Workmentioning

confidence: 99%

“…Like an additional authentication mechanism, the written messages may be e study has been usually conducted in long text, even though authorship authentication with the application of stylometry has been a prominent field. For the identification of authors with regard to the style of their and scholars of the humanities have been together contributing to the development of automated methods during the past 50 years (Rocha, 2016). Each author has have impacts on the forms and contents of written them.…”

Section: Introductionmentioning

confidence: 99%

Better Features Sets for Authorship Attribution of Short Messages

Demir

2017

scjournal

View full text Add to dashboard Cite

Authorship Attribution for Social Media Forensics

Cited by 193 publications

References 122 publications

First Steps towards Data-driven Adversarial Deduplication

First Steps towards Data-driven Adversarial Deduplication

First Steps towards Data-driven Adversarial Deduplication

Better Features Sets for Authorship Attribution of Short Messages

Contact Info

Product

Resources

About