Abstract: Aspects of the present disclosure relate to cryptography. In particular, example embodiments relate to computing a relationship between private data of a first entity and private data of a second entity, while preserving privacy of the entities and preventing inter-entity data sharing. A server includes a first component to compute an intersection of two datasets, without directly accessing either dataset. The server includes a second component to compute a relationship, such as a regression, between data in the first dataset and data in the second dataset, without directly accessing either dataset.

Abstract: In an example embodiment, a machine learning algorithm is used to train an engagement score model to calculate an engagement score for a particular member indicating a probability that the particular member would increase engagement with the social networking service if provided with statistical information about confidential data submitted by other members. Member usage information is obtained corresponding to a first member of a social networking service. Then a plurality of features are extracted from the member usage information corresponding to the first member. This plurality of features is inputted into the engagement model to obtain an engagement score for the first member. It is then determined whether or not to provide statistical information to the first member about confidential data submitted by other members based on the engagement score for the first member.

Abstract: In an example embodiment, a submission of confidential data is received from a user via a first computerized user interface. An identification of the user is obtained, and details regarding the submission are stored in a submission table. Then a request to display, to the user, statistical information derived from confidential data from users other than the user, is received from a second computerized user interface. Based on information stored in the submission table, a determination is made that the request to display, to the user, statistical information derived from confidential data from users other than the user should be granted. In response to the determining, the statistical information derived from confidential data from users other than the user is displayed via the second computerized user interface.

Abstract: In an example embodiment, an attribute interference model is trained by a machine learning algorithm to output missing attribute values from a member profile of a social networking service. In an attribute inference phase, an identification of a member of a social networking service is obtained. A member profile corresponding to the member of the social networking service is retrieved using the identification. The member profile is then passed to the attribute inference model to generate one or more missing attribute values for the member profile. A collection flow, defined in a user interface of a computing device, is modified based on the generated one or more missing attribute values, the collection flow defining a sequence of screens for collecting confidential data. The modified collection flow is then presented to the member in the user interface to collect confidential data from the member.

Abstract: In an example embodiment, a cohort to target is identified, the cohort including a plurality of members of a social networking service having member profiles that all share at least one attribute value. A minimum number of eligible members of the cohort in order to provide relevant statistical insights from confidential data submitted by eligible members of the cohort is identified, and based on an assumed response rate for eligible members of the cohort, a total number of eligible members in the cohort, and the minimum number of eligible members of the cohort in order to provide relevant statistical insights, the eligible members are divided into a first wave and a second wave.

Abstract: In an embodiment, a cohort to target is identified, the cohort including a plurality of members of a social networking service having member profiles that all share at least one attribute value. A minimum number of eligible members needed to provide relevant statistical insights from confidential data submitted by eligible members of the cohort is identified. Then, based on an assumed response rate for eligible members of the cohort, a total number of eligible members in the cohort, and the minimum number of eligible members needed to provide relevant statistical insights, it is determined that an estimated amount of responses to invitations to submit confidential data to eligible members of the cohort is less than the minimum number of eligible members needed to provide relevant statistical insights. In response to the determination, the cohort is altered to include eligible members from at least one other cohort, and the process repeated.

Abstract: In an example embodiment, a method for protecting against timestamp-based inference attacks in a computer system is provided. A timestamp corresponding to a time when confidential data is submitted to the computer system by a user is recorded. A modification value based on a frequency of submissions of confidential data to the computer system is selected. The timestamp is altered by adding the modification value to the timestamp.

Abstract: In an example embodiment, a method for protecting against confidential data-based inference attacks in a computer system is provided. A first confidential data value is received. Then a modification value is selected based on a level of privacy specified for the computer system. Then the first confidential data value is altered by adding the modification value to the first confidential data value.

Abstract: In an example embodiment, an attribute interference model is trained by a machine learning algorithm to output missing attribute values from a member profile of a social networking service. In an attribute inference phase, an identification of a member of a social networking service is obtained. A member profile corresponding to the member of the social networking service is retrieved using the identification. The member profile is then passed to the attribute inference model to generate one or more missing attribute values for the member profile. A collection flow, defined in a user interface of a computing device, is modified based on the generated one or more missing attribute values, the collection flow defining a sequence of screens for collecting confidential data. The modified collection flow is then presented to the member in the user interface to collect confidential data from the member.

Abstract: In an embodiment, a submission history table is maintained by tracking an identification of each user making a submission of a confidential data value and a timestamp of when the corresponding submission was made. A first confidential data value submission is received from a user having a first identification. Member usage information for the user having the first identification, are retrieved based on the first identification. The submission history table is referenced to determine a length of time since the user having the first identification last made a submission of confidential data. It is determined that the user having the first identification is not permitted to submit confidential information based on the member usage information and the length of time since the user having the first identification last made a submission of confidential data. In response to the determining, the first confidential data value is discarded.

Abstract: Aspects of the present disclosure relate to cryptography. In particular, example embodiments relate to computing a relationship between private data of a first entity and private data of a second entity, while preserving privacy of the entities and preventing inter-entity data sharing. A server includes a first component to compute an intersection of two datasets, without directly accessing either dataset. The server includes a second component to compute a relationship, such as a regression, between data in the first dataset and data in the second dataset, without directly accessing either dataset.

Abstract: In an example, a granularity of company similarity is determined, wherein the granularity of company similarity is a level at which social networking data should be filtered. A weighted graph of companies is constructed at the granularity of company similarity, wherein each node in the weighted graph is a company and a directed edge exists in the weighted graph between a first node and a second node if the social networking data, at the granularity of company similarity, indicates that a transition occurred wherein a member who held a position at a company corresponding to the first node transitioned to a position at a company corresponding to the second node, wherein each directed edge contains a weight indicating a strength of relationship between nodes. The weighted graph of locations is traversed from a node corresponding to the target company in order to identify companies similar to the target company.

Abstract: In an example embodiment, an attribute interference model is trained by a machine learning algorithm to output missing attribute values from a member profile of a social networking service. In an attribute inference phase, an identification of a member of a social networking service is obtained. A member profile corresponding to the member of the social networking service is retrieved using the identification. The member profile is then passed to the attribute inference model to generate one or more missing attribute values for the member profile. A collection flow, defined in a user interface of a computing device, is modified based on the generated one or more missing attribute values, the collection flow defining a sequence of screens for collecting confidential data. The modified collection flow is then presented to the member in the user interface to collect confidential data from the member.

Abstract: In an embodiment, a submission history table is maintained by tracking an identification of each user making a submission of a confidential data value and a timestamp of when the corresponding submission was made. A first confidential data value submission is received from a user having a first identification. Member usage information for the user having the first identification, are retrieved based on the first identification. The submission history table is referenced to determine a length of time since the user having the first identification last made a submission of confidential data. It is determined that the user having the first identification is not permitted to submit confidential information based on the member usage information and the length of time since the user having the first identification last made a submission of confidential data. In response to the determining, the first confidential data value is discarded.

Abstract: In an example embodiment, a method for protecting against incorrect confidential data values in a computer system is provided. A machine learning algorithm is used to train a confidential data value quality score based on metrics extracted from member profile and member usage information in a social networking service. The confidential data value quality score model is then used to output an estimated quality score for submitted confidential data values.

Abstract: Aspects of the present disclosure relate to cryptography. In particular, example embodiments relate to computing a relationship between private data of a first entity and private data of a second entity, while preserving privacy of the entities and preventing inter-entity data sharing. A server includes a first component to compute an intersection of two datasets, without directly accessing either dataset. The server includes a second component to compute a relationship, such as a regression, between data in the first dataset and data in the second dataset, without directly accessing either dataset.

Abstract: Aspects of the present disclosure relate to cryptography. In particular, example embodiments relate to computing a relationship between private data of a first entity and private data of a second entity, while preserving privacy of the entities and preventing inter-entity data sharing. A server includes a first component to compute an intersection of two datasets, without directly accessing either dataset. The server includes a second component to compute a relationship, such as a regression, between data in the first dataset and data in the second dataset, without directly accessing either dataset.

Abstract: Generally discussed herein are methods, systems, and apparatuses for harmonizing information from different taxonomies and providing career information based on the harmonized information. A method can include receiving a request for the career information, the request including one or more job titles and one or more job locations associated with the job titles, mapping the one or more job titles to one or more profession titles, mapping the one or more job locations to one or more profession locations, executing a query for statistics associated with the career information, the query including the one or more profession titles and the one or more profession locations to which the one or more job titles and the one or more job locations respectively map, and providing the career information based on the statistics returned from executing the query.

Abstract: A school ranking system may be configured to determine a rank of a school based on career outcomes data. Career outcomes data is obtained, at least in part, from member profile data stored by an on-line social network system. The school ranking system uses a list of the top-ranked companies for generating ranking data and also determines how many companies are to be included in the list of the top-ranked companies.

Abstract: A school ranking system may be configured to determine a rank of a school based on career outcomes data, which may be obtained from member profile data stored by an on-line social network system. Schools may be ranked on the basis of proportions of their graduates who obtained employment at some of the most desirable companies for a given profession or occupation. In order to make university rankings robust to potential noise in company desirability, a large number of perturbed sets of desirable companies are generated by repeatedly substituting a subset of companies from the set of desirable companies with companies outside that set.