c******n
发帖数: 4965 | 1 we are working on some ppc click fraud detection project.
a very hard problem is how to find those clicks which come from "get paid to
click on ads" users, or simply from bots on compromised machines.
for bots, the bots program can decorate their http requests any way they
like, they can write fake cookies, fake referrer, fake landing urls. a lot
of the research on this subject focuses on the frequency per cookie, or try
to look at referrers (reverse spidering), or look at the user's browsing
history (landing url) . but if the bot can fake all these, the analysis on
these features also become useless, right?
the only thing that can not be faked by the bots is the ip. so we have the
very basic, very common frequency per ip analysis. but this is not
effective at all if the fake requests are widely distributed on a
compromised botnet of machines.
anybody working in this field could give some pointers? thanks | s*******e
发帖数: 4188 | 2 n年前afei好像搞过这个
★ 发自iPhone App: ChineseWeb 7.8
【在 c******n 的大作中提到】
: we are working on some ppc click fraud detection project.
: a very hard problem is how to find those clicks which come from "get paid to
: click on ads" users, or simply from bots on compromised machines.
: for bots, the bots program can decorate their http requests any way they
: like, they can write fake cookies, fake referrer, fake landing urls. a lot
: of the research on this subject focuses on the frequency per cookie, or try
: to look at referrers (reverse spidering), or look at the user's browsing
: history (landing url) . but if the bot can fake all these, the analysis on
: these features also become useless, right?
: the only thing that can not be faked by the bots is the ip. so we have the
| w*********m
发帖数: 4740 | 3 knowledge if not free
to
try
【在 c******n 的大作中提到】
: we are working on some ppc click fraud detection project.
: a very hard problem is how to find those clicks which come from "get paid to
: click on ads" users, or simply from bots on compromised machines.
: for bots, the bots program can decorate their http requests any way they
: like, they can write fake cookies, fake referrer, fake landing urls. a lot
: of the research on this subject focuses on the frequency per cookie, or try
: to look at referrers (reverse spidering), or look at the user's browsing
: history (landing url) . but if the bot can fake all these, the analysis on
: these features also become useless, right?
: the only thing that can not be faked by the bots is the ip. so we have the
| m***r
发帖数: 680 | 4 没听过ip spoofing？
to
try
【在 c******n 的大作中提到】
: we are working on some ppc click fraud detection project.
: a very hard problem is how to find those clicks which come from "get paid to
: click on ads" users, or simply from bots on compromised machines.
: for bots, the bots program can decorate their http requests any way they
: like, they can write fake cookies, fake referrer, fake landing urls. a lot
: of the research on this subject focuses on the frequency per cookie, or try
: to look at referrers (reverse spidering), or look at the user's browsing
: history (landing url) . but if the bot can fake all these, the analysis on
: these features also become useless, right?
: the only thing that can not be faked by the bots is the ip. so we have the
| t*******t
发帖数: 1656 | 5 you should ask your CTO.
to
try
【在 c******n 的大作中提到】
: we are working on some ppc click fraud detection project.
: a very hard problem is how to find those clicks which come from "get paid to
: click on ads" users, or simply from bots on compromised machines.
: for bots, the bots program can decorate their http requests any way they
: like, they can write fake cookies, fake referrer, fake landing urls. a lot
: of the research on this subject focuses on the frequency per cookie, or try
: to look at referrers (reverse spidering), or look at the user's browsing
: history (landing url) . but if the bot can fake all these, the analysis on
: these features also become useless, right?
: the only thing that can not be faked by the bots is the ip. so we have the
| a*****r
发帖数: 55 | 6 typical machine learning problem
to
try
【在 c******n 的大作中提到】
: we are working on some ppc click fraud detection project.
: a very hard problem is how to find those clicks which come from "get paid to
: click on ads" users, or simply from bots on compromised machines.
: for bots, the bots program can decorate their http requests any way they
: like, they can write fake cookies, fake referrer, fake landing urls. a lot
: of the research on this subject focuses on the frequency per cookie, or try
: to look at referrers (reverse spidering), or look at the user's browsing
: history (landing url) . but if the bot can fake all these, the analysis on
: these features also become useless, right?
: the only thing that can not be faked by the bots is the ip. so we have the
| s*******e
发帖数: 4188 | 7 Maybe he's the CTO
★ 发自iPhone App: ChineseWeb 7.8
【在 t*******t 的大作中提到】
: you should ask your CTO.
:
: to
: try
| c******n
发帖数: 4965 | 8 ip spoofing requires a much more involved level of click bots, while the
frauds on referrer, cookie etc is only at the level of HTTP requests and can
be easily done in a JS
【在 m***r 的大作中提到】
: 没听过ip spoofing？
:
: to
: try
|
|
