The robustness of a new CAPTCHA

Ahmad Salah El Ahmad; Jeff Yan; Lindsay Marshall

doi:10.1145/1752046.1752052

The robustness of a new CAPTCHA

Ahmad Salah El Ahmad, Jeff Yan, Lindsay Marshall

Computer And Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

66 Citations (Scopus)

Abstract

CAPTCHA is a standard security technology that presents tests to tell computers and humans apart. In this paper, we examine the security of a new CAPTCHA that was deployed until very recently by Megaupload, a leading online storage and delivery website. The security of this scheme relies on a novel segmentation resistance mechanism. However, we show that this CAPTCHA can be segmented using a simple but new automated attack with a success rate of 78%. It takes about 120 ms on average to segment each challenge on a standard desktop computer.

Original language	English
Title of host publication	EUROSEC'10
Subtitle of host publication	Proceedings of the 3rd European Workshop on System Security
Place of Publication	New York, NY
Publisher	Association for Computing Machinery
Pages	36-41
Number of pages	6
ISBN (Print)	9781450300599
DOIs	https://doi.org/10.1145/1752046.1752052
Publication status	Published - 13 Apr 2010
Event	3rd European Workshop on System Security, EUROSEC'10 - Paris, France Duration: 13 Apr 2010 → 13 Apr 2010

Conference

Conference	3rd European Workshop on System Security, EUROSEC'10
Country/Territory	France
City	Paris
Period	13/04/10 → 13/04/10

Keywords

CAPTCHA
Gestalt perception
robustness
segmentation attack

Access to Document

10.1145/1752046.1752052

Cite this

@inproceedings{522c131467c84e39b838ac5400c4ad59,

title = "The robustness of a new CAPTCHA",

abstract = "CAPTCHA is a standard security technology that presents tests to tell computers and humans apart. In this paper, we examine the security of a new CAPTCHA that was deployed until very recently by Megaupload, a leading online storage and delivery website. The security of this scheme relies on a novel segmentation resistance mechanism. However, we show that this CAPTCHA can be segmented using a simple but new automated attack with a success rate of 78\%. It takes about 120 ms on average to segment each challenge on a standard desktop computer.",

keywords = "CAPTCHA, Gestalt perception, robustness, segmentation attack",

author = "\{El Ahmad\}, \{Ahmad Salah\} and Jeff Yan and Lindsay Marshall",

year = "2010",

month = apr,

day = "13",

doi = "10.1145/1752046.1752052",

language = "English",

isbn = "9781450300599",

pages = "36--41",

booktitle = "EUROSEC'10",

publisher = "Association for Computing Machinery",

address = "United States",

note = "3rd European Workshop on System Security, EUROSEC'10 ; Conference date: 13-04-2010 Through 13-04-2010",

}

TY - GEN

T1 - The robustness of a new CAPTCHA

AU - El Ahmad, Ahmad Salah

AU - Yan, Jeff

AU - Marshall, Lindsay

PY - 2010/4/13

Y1 - 2010/4/13

N2 - CAPTCHA is a standard security technology that presents tests to tell computers and humans apart. In this paper, we examine the security of a new CAPTCHA that was deployed until very recently by Megaupload, a leading online storage and delivery website. The security of this scheme relies on a novel segmentation resistance mechanism. However, we show that this CAPTCHA can be segmented using a simple but new automated attack with a success rate of 78%. It takes about 120 ms on average to segment each challenge on a standard desktop computer.

AB - CAPTCHA is a standard security technology that presents tests to tell computers and humans apart. In this paper, we examine the security of a new CAPTCHA that was deployed until very recently by Megaupload, a leading online storage and delivery website. The security of this scheme relies on a novel segmentation resistance mechanism. However, we show that this CAPTCHA can be segmented using a simple but new automated attack with a success rate of 78%. It takes about 120 ms on average to segment each challenge on a standard desktop computer.

KW - CAPTCHA

KW - Gestalt perception

KW - robustness

KW - segmentation attack

UR - https://www.scopus.com/pages/publications/77952349364

U2 - 10.1145/1752046.1752052

DO - 10.1145/1752046.1752052

M3 - Conference contribution book

AN - SCOPUS:77952349364

SN - 9781450300599

SP - 36

EP - 41

BT - EUROSEC'10

PB - Association for Computing Machinery

CY - New York, NY

T2 - 3rd European Workshop on System Security, EUROSEC'10

Y2 - 13 April 2010 through 13 April 2010

ER -

The robustness of a new CAPTCHA

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this