Adversarial information retrieval
Adversarial information retrieval (adversarial IR) is a topic in information retrieval that addresses tasks such as gathering, indexing, filtering, retrieving and ranking information from collections wherein a subset has been manipulated maliciously. Adversarial IR includes the study of methods to detect, isolate, and defeat such manipulation.
On the Web, the predominant form of such manipulation is search engine spamming (also known as spamdexing), including techniques that are employed to disrupt the activity of web search engines, usually for financial gain. Examples of spamdexing are link-bombing, comment or referrer spam, spam blogs (splogs), malicious tagging, reverse engineering of ranking algorithms, advertisement blocking, and web content filtering [1].
The name stems from the fact that there are two sides with opposing goals. For instance, the relationship between the owner of a Web site trying to rank high on a search engine and the search engine administrator is an adversarial relationship in a zero-sum game. Every undeserved gain in ranking by the web site is a loss of precision for the search engine.
Topics
Topics related to Web spam:
- Link spam
- Keyword spamming
- Spam related to blogs, including comment spam and splogs
- Cloaking
Other topics:
- Click fraud
- Reverse engineering of ranking algorithms
- Web content filtering
- Advertisement blocking
- Stealth crawling
History
The term "adversarial information retrieval" was first coined in 2000 by Andrei Broder (then Chief Scientist at Alta Vista) during the Web plenary session at the TREC-9 conference[2].
References
- ^ B. Davison, M. Najork, and T. Converse (2006), SIGIR Worksheet Report: Adversarial Information Retrieval on the Web (AIRWeb 2006)
- ^ D. Hawking and N. Craswell (2004), Very Large Scale Retrieval and Web Search (Preprint version)