@INPROCEEDINGS{,
  author = {Jedidiah R. Crandall and Daniel Zinn and Michael Byrd and Earl Barr
	and Rich East},
  title = {ConceptDoppler: A Weather Tracker for Internet Censorship},
  booktitle = {14th ACM Conference on Computer and Communication Security},
  abbrev = {ccs},
  year = {2007},
  address = {Alexandria, Virginia},
  month = {October},
  abstract = {The text of this paper has passed across many Internet routers on
	its way to the reader, but some routers will not pass it along unfettered
	because of censored words it contains. We present two sets of results:
	1) Internet measurements of keyword filtering by the Great "Firewall"
	of China (GFC); and 2) initial results of using latent semantic analysis
	as an efficient way to reproduce a blacklist of censored words via
	probing.
	
	
	Our Internet measurements suggest that the GFC's keyword filtering
	is more a panopticon than a firewall, i.e., it need not block every
	illicit word, but only enough to promote self-censorship.  China's
	largest ISP, ChinaNET, performed 83.3% of all filtering of our probes,
	and 99.1% of all filtering that occurred at the first hop past the
	Chinese border. Filtering occurred beyond the third hop for 11.8%
	of our probes, and there were sometimes as many as 13 hops past the
	border to a filtering router. Approximately 28.3% of the Chinese
	hosts we sent probes to were reachable along paths that were not
	filtered at all. While more tests are needed to provide a definitive
	picture of the GFC's implementation, our results disprove the notion
	that GFC keyword filtering is a firewall strictly at the border of
	China's Internet.
	
	
	While evading a firewall a single time defeats its purpose, it would
	be necessary to evade a panopticon almost every time. Thus, in lieu
	of evasion, we propose ConceptDoppler, an architecture for maintaining
	a censorship "weather report" about what keywords are filtered over
	time. Probing with potentially filtered keywords is arduous due to
	the GFC's complexity and can be invasive if not done efficiently.
	Just as an understanding of the mixing of gases preceded effective
	weather reporting, understanding of the relationship between keywords
	and concepts is essential for tracking Internet censorship. We show
	that LSA can effectively pare down a corpus of text and cluster filtered
	keywords for efficient probing, present 122 keywords we discovered
	by probing, and underscore the need for tracking and studying censorship
	blacklists by discovering some surprising blacklisted keywords such
	as X  (conversion rate), Y (Mein Kampf), and Z (International geological
	scientific federation (Beijing)).},
  timestamp = {2007.09.12}
}