tag:blogger.com,1999:blog-11891192.post6269593731073449039..comments2023-07-24T22:50:27.802+10:00Comments on irldexter: Arrogance of obfuscation.Donalhttp://www.blogger.com/profile/13772533723547791668noreply@blogger.comBlogger5125tag:blogger.com,1999:blog-11891192.post-58739167031015438262008-11-20T12:05:00.000+11:002008-11-20T12:05:00.000+11:00That's a lot of material. Can you give me a 4 sent...That's a lot of material. Can you give me a 4 sentence guide/summary to start me out on this safari?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-11891192.post-7233998859073728032008-11-20T11:42:00.000+11:002008-11-20T11:42:00.000+11:00It's about de-identification. It's feasible once y...It's about de-identification. It's feasible once you have something to compare. <BR/><BR/>Here is some more info...<BR/><BR/>Privacy-Preservng Data Mining: Models and Algorithms (Advances in Database<BR/>Systems:<BR/># Hardcover: 514 pages<BR/># Publisher: Springer; 1st edition (July 7, 2008)<BR/># Language: English # ISBN-10: 0387709916<BR/><BR/>K-Anonymity and De-identification:<BR/><BR/>K-anonymity (k-Anonymity: a model for protecting privacy)<BR/><A HREF="http://privacy.cs.cmu.edu/people/sweeney/kanonymity.html" REL="nofollow">http://privacy.cs.cmu.edu/people/sweeney/kanonymity.html</A><BR/><A HREF="http://spdp.dti.unimi.it/papers/k-anonymity.pdf" REL="nofollow">http://privacy.cs.cmu.edu/people/sweeney/kanonymity.html</A><BR/><BR/>Also from a colleague on the SecurityMetrics mailing list:<BR/><BR/>"I believe that readers of this mailing list might also be interested<BR/>in the perturbation approach (originally described in<BR/><A HREF="http://www.almaden.ibm.com/cs/projects/iis/hdb/Publications/papers/sigmod00_privacy.pdf" REL="nofollow">http://www.almaden.ibm.com/cs/projects/iis/hdb/Publications/papers/sigmod00_privacy.pdf</A>,<BR/>and covered in chapter 6 in the book). This method is suitable for<BR/>survey-like data collection: you mask data by adding noise, but some<BR/>statistical properties are maintained despite the noise.<BR/>Unfortunately, research shows that the perturbation methods suggested<BR/>so far are susceptible to various attacks (chapter 15)."Donalhttps://www.blogger.com/profile/13772533723547791668noreply@blogger.comtag:blogger.com,1999:blog-11891192.post-76374840041023544752008-11-20T11:36:00.000+11:002008-11-20T11:36:00.000+11:00This comment has been removed by the author.Donalhttps://www.blogger.com/profile/13772533723547791668noreply@blogger.comtag:blogger.com,1999:blog-11891192.post-35966482930908069172008-11-20T11:21:00.000+11:002008-11-20T11:21:00.000+11:00Can you expand a bit more on how, and in what prec...Can you expand a bit more on how, and in what precise circumstances, the data can be disaggregated to show individual's DNA.<BR/><BR/>I am not familiar with how aggregated data is presented, but in a purely statistical case it would not be possible to disaggregate anonymised samples.<BR/><BR/>In a real laboratory situation with specimen samples I can see the advantages of this refinement.<BR/><BR/>In aggregate presentations I don't, on the face of it, see the problem.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-11891192.post-27642611849604542742008-11-19T04:08:00.000+11:002008-11-19T04:08:00.000+11:00Hi,I want to know more. I've started a genetic te...Hi,<BR/><BR/>I want to know more. I've started a genetic testing company that is handling our consumer data differently than 23andMe and Navigenics (not sharing it with other groups, even if "anonymized" and aggregated), but I'm always interested in potential improvement.<BR/>We have to convey our information to our customers over a network somehow. They login to see their results at their account.<BR/>How could a SCADA system make this better?<BR/>Educate me please.<BR/>-Tera Eerkes<BR/>teerkes@qtrait.comteerkeshttps://www.blogger.com/profile/16936034766016711829noreply@blogger.com