On Random Field Completely Automated Public Turing Test to Tell Computers and Humans Apart Generation

Kouritzin, Michael A.; Newton, Fraser; Wu, Bi

doi:10.1109/tip.2012.2236342

Cited by 14 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is equivalent to ensuring that the recursive formula (2.5) of Proposition 1 produces a conditional pmf in every iteration. It was observed in our CAPTCHA Kouritzin et al (2013) and OCR Kouritzin et al (2014) applications that the occasional illegitimate conditional pmf value outside [0, 1] can be replaced with a value inside without noticeable effect on the simulation. Fig.…”

Section: Introductionmentioning

confidence: 86%

“…The one-pass algorithm (as opposed to the Gibbstype algorithm used in Kouritzin et al (2013)) follows from (3.1). We just use the conditional probability to simulate the new vertex given the prior ones in the topological sort.…”

Section: Remarkmentioning

confidence: 99%

“…The approach has been applied to Optical Character Recognition (OCR) Kouritzin et al (2014) and the generation of both black-and-white Kouritzin et al (2013) and gray-level Newton and Kouritzin (2011) CAPTCHAs ( Fig. 1 shows a new example of such a gray level CAPTCHA.)…”

Section: Introductionmentioning

confidence: 99%

“…The joint distribution between pairs of vertices connected by a specified covariance edge is known in terms of two sets of auxiliary parameter pmf collections that can be selected for generality. However, the joint subgraph distribution on an incomplete subgraph is unknown for the algorithm in Kouritzin et al (2013).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Flexible, Real-Time Algorithm for Simulating Correlated Random Fields and Its Properties

Kouritzin¹,

Newton²,

Wu³

2017

Journal of Mathematics and Statistics

Self Cite

View full text Add to dashboard Cite

Contemporary real-time problems like CAPTCHA generation and optical character recognition can be solved effectively using correlated random fields. These random fields should be produced on a graph in order that problems of any dimension and shape can be handled. However, traditional solutions are often too slow, inaccurate or both. Herein, the Quick Simulation Random Field algorithm to produce correlated random fields on general undirected graphs is introduced. It differs from prior algorithms by completing the graph and setting the unspecified covariances to zero, which facilitates analytic study. The Quick Simulation Random Field graph distribution is derived within and the following questions are studied: (1) For which marginal pmfs and covariances will this algorithm work? (2) When does the marginal property hold, where the sub-graph distribution of an algorithm-simulated field matches the distribution of the algorithm-simulated field on the subgraph? (3) When does the permutation property hold, where the vertex simulation order does not affect the joint distribution?

show abstract

Section: Introductionmentioning

confidence: 86%

Section: Remarkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Flexible, Real-Time Algorithm for Simulating Correlated Random Fields and Its Properties

Kouritzin¹,

Newton²,

Wu³

2017

Journal of Mathematics and Statistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…KNW -CAPTCHA [4] is created using Scatter type algorithm. Pessimal noise is created using Scatter type algorithm.…”

Section: Figure 3 Ez -Gimpy [10]mentioning

confidence: 99%

Avoidance of Password Guessing Using Completely Automated Public Turing Test

Navamani

Banu

2014

2014 International Conference on Intelligent Computing Applications

View full text Add to dashboard Cite

CAPTCHA will demonstrate information about word tests for easy human recognition. CAPTCHA used to differentiate human and non -human or bots.Gibbs resampling repeatedly generate random word until the word becomes human-readable. Passwords are commonly used for authentication purpose. Two types of attacks are Brute Force attack and Dictionary Attack. Those attacks can be avoided using CAPTCHA. Bots using Optical Character Recognition (OCR) program for tracing CAPTCHAs.

show abstract

Machine learning and empathy: the Civil Rights CAPTCHA

Hernández-Castro

Barrero

R-Moreno

2015

Concurrency and Computation

View full text Add to dashboard Cite

Human interactive proofs (HIPs) are a basic security measure on the Internet to avoid automatic attacks. There is an ongoing effort to find a HIP that is secure enough yet easy for humans. Recently, a new HIP has been designed aiming at higher security: the Civil Rights Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA). It employs the empathy capacity of humans to further strengthen Securimage, a well-known text CAPTCHA. In this paper, we analyze it from a security perspective, finding fundamental design flaws. Using several well-known machine learning (ML) algorithms, we analyze to what extent these flaws affect its security. We discover that thanks to them, we can create a successful side-channel attack. This attack is able to correctly solve the HIP on 20:7% of occasions, much more than enough to consider it broken. Thus, we show that there is no need to solve the problem of optical character recognition nor empathy analysis for computers to break this particular HIP. ML can be successfully used to break a HIP that uses both with a side-channel attack. This security analysis can be applied to other HIPs. It will allow to test whether they are leaking too much information by unexpected ways, given non-evident design flaws.

show abstract

On Random Field Completely Automated Public Turing Test to Tell Computers and Humans Apart Generation

Cited by 14 publications

References 16 publications

A Flexible, Real-Time Algorithm for Simulating Correlated Random Fields and Its Properties

A Flexible, Real-Time Algorithm for Simulating Correlated Random Fields and Its Properties

Avoidance of Password Guessing Using Completely Automated Public Turing Test

Machine learning and empathy: the Civil Rights CAPTCHA

Contact Info

Product

Resources

About