WWW.IJITECH.ORG
ISSN 2321-8665
Vol.04,Issue.19,
December-2016,
Pages:3765-3768
Authentication of Gross Trickery in Application Distribution
REEHANA SYED1, G.MANTHRU NAIK2, P.G.K.SIRISHA3
1
PG Scholar, Dept of CSE, SMITW, Guntur, AP, India.
Assistant Professor, Dept of CSE, SMITW, Guntur, AP, India.
3
Associate Professor & HOD, Dept of CSE, SMITW, Guntur, AP, India.
2
Abstract: The Mobile App is famous among mobile devices
as mobile users are increasing gradually. But due to increase
of applications fault gross is the main problem to observe.
Fault gross means susceptible ways by which increasing the
in demand table. The importance and necessity of minimizing
fault gross is well known. In the existing system the
prominent event and prominent period of an app is identified
from the collected historical records. We use three types of
attestations which are retrieved from user. They are Gross
attestation, survey attestation, audit attestation. By composing
these three attestation methods proof can be formed. We are
proposing two improvements. Firstly, we are using Approval
of scores by the admin to analyze the exact audits and survey
scores. Secondly, the fault assessment for increasing the
popularity of the of the application in the top list is avoided.
Two distinctive restraints are validated for verifying the
assessment given to an application. The first constraint is that
an app can be rated only once from a user login and the
second is implemented with the aid of IP address that limits
the user login logged per day. Finally, the planned system will
be evaluated with real-world App data which is to be
collected from the App Store for a long time period.
Keywords: Mobile Apps, Gross Fraud Detection, Attestation
Aggregation, Historical Gross Records, Survey and Audit.
I. INTRODUCTION
Gross fraud in the mobile app market refers to fake or
deceptive activities which have a purpose of bumping up the
apps in the popularity list. Indeed, it becomes more and more
frequent for app developers to use shady means, such as
inflating their apps‟ sales or posting phony App surveys, to
commit gross fraud. While the importance of preventing gross
fraud has been widely recognized, there is limited
understanding and research in this area. To this end, in this
paper, we provide a holistic view of gross fraud and propose a
gross fraud detection system for mobile apps. Specifically, we
first propose to accurately locate the gross fraud by mining
the active periods, namely prominentperiods, of mobile Apps.
Such prominentperiods can be leveraged for detecting the
local anomaly instead of global anomaly of app gross.
Furthermore, we investigate three types of attestations, i.e.,
gross based attestations, survey based attestations and audit
based attestations, by modeling apps‟ gross, survey and audit
behaviors through statistical hypotheses tests. In Survey
Based Attestations, specifically, after an App has been
published, it can be rated by any user who downloaded it.
Indeed, user survey is one of the most important features of
App advertisement. An App which has higher survey may
attract more users to download and can also be ranked higher
in the leader board. Thus, survey manipulation is also an
important perspective of gross fraud. In Audit Based
Attestations, besides surveys, most of the App stores also
allow users to write some textual comments as App audits.
Especially, this paper proposes a simple and effective
algorithm to recognize the prominentperiods of each mobile
App based on its historical gross records. This is one of the
fraud attestation. Also, survey and audit history, which gives
some anomaly patterns from apps historical survey and audits
records. The rest of the paper is organized as follows: Section
II, presents the literature survey over the related work. In
section III, planned system is presented in section IV,
implementation for each modules. Finally, the section V
concludes the audit paper
II. LITERATURE SURVEY
Leif Azzopardi et al. [2] studied an Investigating the
Relationship between Language Model Perplexity and IR
Precision Recall Measures the perplexity of the language
model has a systematic relationship with the achievable
precision recall performance though it is not statistically
significant. A latent variable unigram based LM, which has
been successful when applied to IR, is the so called
probabilistic latent semantic indexing (PLSI). Ee-Peng Lim et
al. presented a number of detecting Product Audit Spammers
using Survey Behaviors to detect users gene survey spam
audits or audit spammers. We identify several characteristic
behaviors of audit spammers and model these behaviors so as
to detect the spammers. David F. Gleich et al. [4] has done a
survey on Rank Aggregation via Nuclear Norm Minimization
the process of rank aggregation is Intimately intertwined with
the structure of skew-symmetric matrices. To produces a new
method for gross a set of items. The essence of our idea is that
a rank aggregation describes a partially filled skew-symmetric
matrix. We extend an algorithm for matrix completion to
handle skew-symmetric data and use that to extract ranks for
each item.
Copyright @ 2016 IJIT. All rights reserved.
REEHANA SYED, G.MANTHRU NAIK, P.G.K.SIRISHA
with normal Apps. Mining Prominent Periods: There are two
III. PLANNED SYSTEM
Detection of gross fraud for mobile Apps is still under a
main steps for mining prominentperiods. First, we need to
subject to research. To fill this crucial lack, we propose to
discover prominent events from the Applications historical,
develop a gross fraud detection system for mobile Apps. We
gross records. Second, we need to merge adjacent prominent
also determine several important challenges. First challenge,
events for constructing prominentperiods.
in the whole life cycle of an App, the gross fraud does not
always happen, so we need to detect the time when fraud
B. Gross Based Attestations
happens. This challenge can be considered as detecting the
A prominent period is composed of several prominent
local anomaly in place of global anomaly of mobile Apps.
events. Therefore, we should first analyze the basic
Second challenge, it is important to have a scalable way to
characteristics of prominent events for extracting fraud
positively detect gross fraud without using any basis
attestations. By analyzing the Apps‟ historical gross records,
information, as there are huge number of mobile Apps, it is
we observe that Apps‟ gross behaviors in a prominent event
very difficult to manually label gross fraud for each App.
always satisfy a specific gross pattern, which consists of three
Finally, due to the dynamic nature of chart gross, it is difficult
different gross phases, namely, rising phase, maintaining
to find and verify the attestations associated with gross fraud,
phase and recession phase. Specifically, in each prominent
which motivates us to discover some implicit fraud patterns of
event, an Applications gross first increases to a peak position
mobile Apps as attestations.
in the leader board (i.e., rising phase), then keeps such peak
position for a period (i.e., maintaining phase), and finally
decreases till the end of the event (i. e., recession phase).
Fig.1. Architecture Diagram
Mobile app stores launched many apps daily in the
leader boards which shows the chart gross of popular apps.
The leader board is the important for promoting apps.
Original application grade level decreases due to the arrival of
fake apps. The users who are newly logging to the app stores,
they decide based on the existing gross, survey, audits for the
individual apps. In recent activities duplicate version of an
application not burned or blocked. This is the major defect.
Higher rank leads huge number of downloads and the app
developer will get more profit. In this they allow Fake
Application also. User not understanding the Fake Apps then
the user also give the audits in the fake application. Exact
Audit or Surveys or Gross Percentage are not correctly
Calculated. In this paper we introduce admin to manage the
gross attestation to minimize the arrival of fake apps, then the
survey and audits are correctly calculated.
IV. IMPLEMENTATION
A. Identifying Prominent Periods
Gross fraud usually happens in prominentperiods.
Therefore, detecting gross fraud of mobile Apps is actually to
detect gross fraud within prominentperiods of mobile Apps.
Specifically, we first propose a simple yet effective algorithm
to identify the prominentperiods of each App based on its
historical gross records. Then, with the analysis of Apps‟
gross „behaviors, we find that the fake Apps often have
different gross patterns in each prominent period compared
C. Survey Based Attestations
The gross based attestations are useful for gross fraud
detection. However, sometimes, it is not sufficient to only use
gross based attestations. Specifically, after an App has been
published, it can be rated by any user who downloaded it.
Indeed, user survey is one of the most important features of
App advertisement. An App which has higher survey may
attract more users to download and can also be ranked higher
in the leader board. Thus, survey manipulation is also an
important perspective of gross fraud. Intuitively, if an App
has gross fraud in a prominent period s, the surveys during the
time period of s may have anomaly patterns compared with its
historical surveys, which can be used for constructing survey
based attestations.
Fig.2. Survey Based Attestation
D. Audit Based Attestations
Besides surveys, most of the App stores also allow users
to write some textual comments as App audits. Such audits
can reflect the personal perceptions and usage experiences of
existing users for particular mobile Apps. Indeed, audit
manipulation is one of the most important perspectives of
App gross fraud. Specifically, before downloading or
purchasing a new mobile App, users often firstly 5, read its
historical audits to ease their decision making, and a mobile
App contains more positive audits may attract more users to
download. Therefore, imposters often post fake audits in the
prominent periods of a specific App in order to inflate the
International Journal of Innovative Technologies
Volume.04, Issue No.19, December-2016, Pages: 3765-3768
Authentication of Gross Trickery in Application Distribution
App downloads, and thus propel the Applications gross
position in the leader board. Although some previous works
on audit spam detection have been reported in recent years,
the problem of detecting the local anomaly of audits in the
prominent periods and capturing them as attestations for gross
fraud detection are still under-explored.
Fig.3. Survey Based Attestation
V. RESULTS
Fig.6. User Mobile App Store which Contain the App
Details to Check the Ranking, Download Rating, Global
Review.
Fig.4. Uploading App by the Admin.
Fig.7. Ranking Deceit for Mobile Apps by Global Review
VI. CONCLUSION AND FUTURE ENHANCEMENT
We developed a gross fraud detection system for mobile
Apps. Specifically, we first showed that gross fraud happened
in prominent periods and provided a method for mining
prominent periods for each App from its historical gross
records. Then, we identified gross based attestations, survey
based attestations and audit based attestations for detecting
gross fraud. Moreover, we planned an optimization based on
admin verification method for evaluating the credibility of
prominent periods from mobile Apps. An unique perspective
of this approach is that all the attestations can be model by
statistical hypothesis tests, thus it is easy to be extended with
other attestations from domain knowledge to detect gross
fraud. The admin can detect the gross fraud for mobile
application. The Audit or Survey or Gross given by users is
correctly calculated. Hence, a new user who wants to
download an app for some purpose can get clear view about
Fig.5. Fake Ranking Given by the Hacker for a Mobile
App Which is Uploaded by Admin.
International Journal of Innovative Technologies
Volume.04, Issue No.19, November-2016, Pages: 3765-3768
REEHANA SYED, G.MANTHRU NAIK, P.G.K.SIRISHA
the available applications. Finally; we validate the planned
system with extensive experiments on real-world App data
collected from the App store. Experimental results showed the
effectiveness of the planned approach. In the future, we plan
to study more effective fraud attestations and analyze the
latent relationship among survey, audit and gross. Moreover,
we will extend our gross fraud detection approach with other
mobile App related services, such as mobile Apps
recommendation, for enhancing user experience.
VII. REFERENCES
[1]Hengshu Zhu, Hui Xiong,Yong Ge, and Enhong Chen,
“Discovery of Gross Fraud for Mobile Apps”in Proc. IEEE
27th Int. Conf. Transactions on knowledge and data
engineering, 2015, pp. 74-87.
[2]L. Azzopardi, M. Girolami, and K. V. Risjbergen,
“Investigating the relationship between language model
perplexity and in precision- recall measures,” in Proc. 26th
Int. Conf. Res. Develop. Inform. Retrieval, 2003, pp. 369–
370.
[3]Y. Ge, H. Xiong, C. Liu, and Z.-H. Zhou, “A taxi driving
fraud detection system,” in Proc. IEEE 11th Int. Conf. Data
Mining, 2011, pp. 181–190.
[4]D. F. Gleich and L.-h. Lim, “Rank aggregation via nuclear
norm minimization,” in Proc. 17th ACM SIGKDD Int. Conf.
Knowl. Discovery Data Mining, 2011, pp. 60–68.
[5]T. L. Griffiths and M. Steyvers, “Finding scientific topics,”
Proc. Nat. Acad. Sci. USA, vol. 101, pp. 5228–5235, 2004.
[6] (2012). [Online]. Available:http://www.ling.gu.se/lager/
mogul/porter-stemmer.
[7] Y. Ge, H. Xiong, C. Liu, and Z.-H. Zhou, “A taxi driving
Proc. IEEE 11th Int. Conf. Data Mining , 2011,pp. 181–190.
International Journal of Innovative Technologies
Volume.04, Issue No.19, December-2016, Pages: 3765-3768