iBGP: A Bipartite Graph Propagation Approach for Mobile Advertising Fraud Detection

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/misy/volume-2017/6412521/figures/6412521.fig.002a.svgz" name="6412521.fig.002a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Ads viewed by users</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/misy/volume-2017/6412521/figures/6412521.fig.002b.svgz" name="6412521.fig.002b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Apps used by users</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/misy/volume-2017/6412521/figures/6412521.fig.002c.svgz" name="6412521.fig.002c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>IPs used by users</td></tr><tr class="fig-image" id="d"><td><object data="https://static.hindawi.com/articles/misy/volume-2017/6412521/figures/6412521.fig.002d.svgz" name="6412521.fig.002d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>User pertinence</td></tr></table>

<div>Characteristics of mobile app users within a one-day period: the behavior patterns of mobile users can be generally described by power law distributions as shown in (a), (b), and (c). (d) Higher mean square pertinence tend to correlate with lower mean interval for non-seed users.</div>

Mobile Information Systems

fig2

Figure 2

Figure 2: iBGP: A Bipartite Graph Propagation Approach for Mobile Advertising Fraud Detection 