Adversarial information retrieval: Difference between revisions
Wikilinked web content filtering |
Cleanup |
||
| Line 1: | Line 1: | ||
'''Adversarial information retrieval''' ('''adversarial IR''') is a topic in [[information retrieval]] related to strategies for working with a data source where some portion of it has been manipulated maliciously. Tasks can include gathering, indexing, filtering, retrieving and ranking information from such a data source. Adversarial IR includes the study of methods to detect, isolate, and defeat such manipulation. |
'''Adversarial information retrieval''' ('''adversarial IR''') is a topic in [[information retrieval]] related to strategies for working with a data source where some portion of it has been manipulated maliciously. Tasks can include gathering, indexing, filtering, retrieving and ranking information from such a data source. Adversarial IR includes the study of methods to detect, isolate, and defeat such manipulation. |
||
On the Web, the predominant form of such manipulation is [[spamdexing|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 [[Google bomb|link-bombing]], [[comment spam|comment]] or [[referrer spam]], [[spam blog]]s (splogs), malicious tagging. Reverse engineering of [[ranking function|ranking algorithms]], [[Ad filtering|advertisement blocking]], and [[web content filtering]] may also be considered forms of adversarial data manipulation. |
On the Web, the predominant form of such manipulation is [[spamdexing|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 [[Google bomb|link-bombing]], [[comment spam|comment]] or [[referrer spam]], [[spam blog]]s (splogs), malicious tagging. Reverse engineering of [[ranking function|ranking algorithms]], [[Ad filtering|advertisement blocking]], and [[web content filtering]] may also be considered forms of adversarial data manipulation.<ref>B. Davison, M. Najork, and T. Converse (2006), [http://www.acm.org/sigs/sigir/forum/2006D/2006d_sigirforum_davison.pdf SIGIR Worksheet Report: Adversarial Information Retrieval on the Web (AIRWeb 2006)]</ref> |
||
Activities intended to poison the supply of useful data make search engines less useful for users. If search engines are more exclusionary they risk becoming more like directories and less dynamic. |
Activities intended to poison the supply of useful data make search engines less useful for users. If search engines are more exclusionary they risk becoming more like directories and less dynamic. |
||
Revision as of 21:05, 30 November 2011
Adversarial information retrieval (adversarial IR) is a topic in information retrieval related to strategies for working with a data source where some portion of it has been manipulated maliciously. Tasks can include gathering, indexing, filtering, retrieving and ranking information from such a data source. 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 may also be considered forms of adversarial data manipulation.[1]
Activities intended to poison the supply of useful data make search engines less useful for users. If search engines are more exclusionary they risk becoming more like directories and less dynamic.
Topics
Topics related to Web spam (spamdexing):
- Link spam
- Keyword spamming
- Cloaking
- Malicious tagging
- Spam related to blogs, including comment spam, splogs, and ping spam
Other topics:
- Click fraud detection
- Reverse engineering of a search engine's ranking algorithm
- Web content filtering
- Advertisement blocking
- Stealth crawling
- Malicious tagging or voting in social networks
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].
See also
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)
External links
- AIRWeb: series of workshops on Adversarial Information Retrieval on the Web
- Web Spam Challenge: competition for researchers on Web Spam Detection
- Web Spam Datasets: datasets for research on Web Spam Detection