Preventing the distribution of forbidden network content using automatic variant detection

A method for preventing distribution of forbidden content, comprising:

• receiving content for distribution over a data communication network;
• updating a list of forbidden variants of forbidden terms for use in blocking distribution of content that presents any of the forbidden variants, the updating comprising:
• accessing a data source that includes a set of received queries that were received from client devices and for which results were returned to the client devices;
• identifying, in the data source, a subset of the received queries that were each adjusted to include a forbidden term in place of, or in addition to, one or more words of the received query prior to using the received query to identify a result in response to the received query;
• identifying, in the subset of received queries, candidate variants of the forbidden term, wherein each candidate variant is a word or phrase that (i) is included in at least one received query of the subset of received query and (ii) caused a search engine to adjust the at least one received query to include the forbidden term;
• determining a score for each candidate variant based on a number of the received queries in the subset of received queries for which the candidate variant caused the search engine to adjust the received queries to include the forbidden term in the received query;
• selecting, from the candidate variants, a set of forbidden variants of the forbidden term based at least on the score for each candidate variant;
• and
• adding the set of forbidden variants to the list of forbidden variants;
• and
• preventing distribution of content that depicts any forbidden variant in the list of forbidden variants.

A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more data processing apparatus cause the data processing apparatus to perform operations comprising:

• receiving content for distribution over a data communication network;
• updating a list of forbidden variants of forbidden terms for use in blocking distribution of content that presents any of the forbidden variants, the updating comprising:
• accessing a data source that includes a set of received queries that were received from client devices and for which results were returned to the client devices;
• identifying, in the data source, a subset of the received queries that were each adjusted to include a forbidden term in place of, or in addition to, one or more words of the received query prior to using the received query to identify a result in response to the received query;
• identifying, in the subset of received queries, candidate variants of the forbidden term, wherein each candidate variant is a word or phrase that (i) is included in at least one received query of the subset of received queries and (ii) caused a search engine to adjust the at least one received query to include the forbidden term;
• determining a score for each candidate variant based on a number of the received queries in the subset of received queries for which the candidate variant caused the search engine to adjust the received query to include the forbidden term in the received query;
• selecting, from the candidate variants, a set of forbidden variants of the forbidden term based at least on the score for each candidate variant;
• and
• adding the set of forbidden variants to the list of forbidden variants;
• and
• preventing distribution of content that depicts any forbidden variant in the list of forbidden variants.