CoChat
Sign Up
Cited by 261Authorship Attribution and ProfilingUser Authentication and Security SystemsInternet Traffic Analysis and Secure E-voting

On the Feasibility of Internet-Scale Author Identification

Narayanan, Arvind, Paskov, Hristo, Gong, Neil Zhenqiang, Bethencourt, John, Stefanov, Emil, Shin, Eui Chul Richard, Song, Dawn·2012·2012 IEEE Symposium on Security and Privacy
DOI 10.1109/sp.2012.46
Open this paper in CoChat — free account

Abstract

We study techniques for identifying an anonymous author via linguistic stylometry, i.e., comparing the writing style against a corpus of texts of known authorship. We experimentally demonstrate the effectiveness of our techniques with as many as 100,000 candidate authors. Given the increasing availability of writing samples online, our result has serious implications for anonymity and free speech -- an anonymous blogger or whistleblower may be unmasked unless they take steps to obfuscate their writing style. While there is a huge body of literature on authorship recognition based on writing style, almost none of it has studied corpora of more than a few hundred authors. The problem becomes qualitatively different at a large scale, as we show, and techniques from prior work fail to scale, both in terms of accuracy and performance. We study a variety of classifiers, both "lazy" and "eager," and show how to handle the huge number of classes. We also develop novel techniques for confidence estimation of classifier outputs. Finally, we demonstrate stylometric authorship recognition on texts written in different contexts. In over 20% of cases, our classifiers can correctly identify an anonymous author given a corpus of texts from 100,000 authors; in about 35% of cases the correct author is one of the top 20 guesses. If we allow the classifier the option of not making a guess, via confidence estimation we are able to increase the precision of the top guess from 20% to over 80% with only a halving of recall.

Integrity signals

Registry

Crossref · 10.1109/sp.2012.46

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Earlier academic work created gold-standard fraud datasets using rule-based heuristics that assume fraudsters post reviews within short intervals, from one IP address, or with skewed rating distributions.

    “academic work has built gold standard fraud datasets using rule-based heuristics, assuming that e.g., fraudsters post reviews in a short period of time [32,33,40,44,87], from the same IP address [40], or have a skewed rating distribution [58,87].”

    From Fraud De-Anonymization for Fun and Profit (2018) · cites this paper as [40]

  • Specialized fraud workers control multiple user accounts and seek employment from product developers to post fake reviews or activities.

    “Specialized fraud workers (also referred to as fraud freelancers, or fraudsters) control multiple user accounts and seek employment by product developers to post fake reviews or activities for their products.”

    From Fraud De-Anonymization for Fun and Profit (2018) · cites this paper as [40]

Cites

Flagged first, then by citations

5 of the 61 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Narayanan, A., Paskov, H., Gong, N. Z., Bethencourt, J., Stefanov, E., Shin, E. C. R., & Song, D.
Affiliations
  • Stanford University (US)
  • University of California, Berkeley (US)
ORCID
Venue
2012 IEEE Symposium on Security and Privacy
Publisher
IEEE
Published
2012-05
Pages
300-314
ISSN
1081-6011 (ISSN-L)
DOI
10.1109/sp.2012.46
OpenAlex
W2077414053
Cited by
261
References
61
Citations by year
2026: 3 · 2025: 4 · 2024: 6 · 2023: 13 · 2022: 11 · 2021: 25 · 2020: 18 · 2019: 26 · 2018: 28 · 2017: 21 · 2016: 20 · 2015: 24 · 2014: 29 · 2013: 26 · 2012: 7
FWCI
21.10
Type
conference paper
Language
en
Open access
closed
Licence
Locations
IEEE Symposium on Security and Privacy (S&P) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
  • Physical Sciences › Computer Science › Information Systems › User Authentication and Security Systems
  • Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
Keywords
authorship attribution, stylometry, anonymous authorship, online anonymity, freedom of expression, writing style

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review