Scaup - Revision history

AdminUser at 16:56, 12 January 2021

2021-01-12T16:56:28Z

AdminUser at 16:39, 12 January 2021

2021-01-12T16:39:45Z

AdminUser at 16:34, 12 January 2021

2021-01-12T16:34:51Z

AdminUser at 16:32, 12 January 2021

2021-01-12T16:32:39Z

AdminUser at 16:24, 12 January 2021

2021-01-12T16:24:57Z

AdminUser at 16:12, 12 January 2021

2021-01-12T16:12:05Z

AdminUser: Created page with "The goal of Google's Scaup is to provide marketers look-alike modeling capabilities, without providing access to event data.https://github.com/goo..."

2021-01-12T15:47:05Z

Created page with "The goal of Google's Scaup is to provide marketers look-alike modeling capabilities, without providing access to event data.<ref>https://github.com/goo..."

New page

The goal of Google's Scaup is to provide marketers [[Look-alike modeling|look-alike modeling]] capabilities, without providing access to event data.<ref>https://github.com/google/ads-privacy/tree/master/proposals/scaup</ref>

Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its information to one trusted server to build models and a second trusted server to apply them. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.

== Impact ==
Prospecting is a critical activity for marketers. Prospecting chooses audiences that are believed to be more likely to become new customers. By centralizing control over this important function, marketers will have less choice on the vendors they can use.

Another potential impact is given the time delay in this look-alike modeling process assigning a given web client eligibility for a new audience attribute, the user experience will be diminished.

== Open Questions ==
* Given each marketer would like to generate different look-alike models for different products, how much data is required to be sent and stored on the web client?

== References ==

<references />

[[Category:Glossary|Scaup]]
[[Category:Privacy Sandbox|Scaup]]

@@ Line 1: / Line 1: @@
 The goal of Google's Scaup is to provide marketers [[Look-alike modeling|look-alike modeling]] capabilities, without providing marketers access to event data.<ref>https://github.com/google/ads-privacy/tree/master/proposals/scaup</ref>
-Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to two trusted servers to build models and another source to apply them. Each of the MPC servers must store historical data to be used as inputs into the modeling. However, under current design the MPC servers are not provide complete information.
+Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends an encrypted version of its personal information to two trusted servers to build models and the outputs of these models is stored for later application. Each of the MPC servers must store historical data to be used as inputs into the modeling. However, under current design the MPC servers are not provided complete information.
 MPC means that so long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being "honest" with its calculations it can be detected. "Honest" means that the result is mathematically accurate.

@@ Line 3: / Line 3: @@
 Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to two trusted servers to build models and another source to apply them. Each of the MPC servers must store historical data to be used as inputs into the modeling. However, under current design the MPC servers are not provide complete information.
-MPC means that so long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being "honest" with its calculations it can be detected. "Honest" means that the result is mathematically accurate. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
+MPC means that so long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being "honest" with its calculations it can be detected. "Honest" means that the result is mathematically accurate.
 Under this proposal, the marketer is allowed to push the machine learning model to the trusted server. The trusted server informs the browser to store the events and features that would be inputs into the machine learning model.

@@ Line 3: / Line 3: @@
 Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to two trusted servers to build models and another source to apply them. Each of the MPC servers must store historical data to be used as inputs into the modeling. However, under current design the MPC servers are not provide complete information.
-MPC means that so long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being honest with its calculations it can b detected. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
+MPC means that so long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being "honest" with its calculations it can be detected. "Honest" means that the result is mathematically accurate. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
 Under this proposal, the marketer is allowed to push the machine learning model to the trusted server. The trusted server informs the browser to store the events and features that would be inputs into the machine learning model.

@@ Line 1: / Line 1: @@
 The goal of Google's Scaup is to provide marketers [[Look-alike modeling|look-alike modeling]] capabilities, without providing marketers access to event data.<ref>https://github.com/google/ads-privacy/tree/master/proposals/scaup</ref>
-Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to two trusted servers to build models and another source to apply them. Each of the MPC servers must store historical data to be used as inputs into the modeling. So long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being honest with its calculations it can b detected. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
+Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to two trusted servers to build models and another source to apply them. Each of the MPC servers must store historical data to be used as inputs into the modeling. However, under current design the MPC servers are not provide complete information.
 Under this proposal, the marketer is allowed to push the machine learning model to the trusted server. The trusted server informs the browser to store the events and features that would be inputs into the machine learning model.

@@ Line 1: / Line 1: @@
 The goal of Google's Scaup is to provide marketers [[Look-alike modeling|look-alike modeling]] capabilities, without providing marketers access to event data.<ref>https://github.com/google/ads-privacy/tree/master/proposals/scaup</ref>
-Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to one trusted server to build models and a second trusted server to apply them. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
+Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to two trusted servers to build models and another source to apply them. Each of the MPC servers must store historical data to be used as inputs into the modeling. So long as one of these servers is trusted to be accountable, then there is a guarantee that if the other server is not being honest with its calculations it can b detected. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
 Under this proposal, the marketer is allowed to push the machine learning model to the trusted server. The trusted server informs the browser to store the events and features that would be inputs into the machine learning model.
 == Impact ==
@@ Line 9: / Line 11: @@
 Another potential impact is given the time delay in this look-alike modeling process assigning a given web client eligibility for a new audience attribute, the user experience will be diminished.

@@ Line 1: / Line 1: @@
-The goal of Google's Scaup is to provide marketers [[Look-alike modeling|look-alike modeling]] capabilities, without providing access to event data.<ref>https://github.com/google/ads-privacy/tree/master/proposals/scaup</ref>
+The goal of Google's Scaup is to provide marketers [[Look-alike modeling|look-alike modeling]] capabilities, without providing marketers access to event data.<ref>https://github.com/google/ads-privacy/tree/master/proposals/scaup</ref>
-Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its information to one trusted server to build models and a second trusted server to apply them. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
+Google's Scaup proposal relies on Multi-Party Computation (MPC) whereby the web client sends its personal information to one trusted server to build models and a second trusted server to apply them. The web client periodically queries the trusted server to receive guidance on whether it belongs to a look-alike model.
 == Impact ==
@@ Line 11: / Line 13: @@
 == Open Questions ==
 * Given each marketer would like to generate different look-alike models for different products, how much data is required to be sent and stored on the web client?
 == References ==