{"id":847,"date":"2007-08-03T09:32:40","date_gmt":"2007-08-03T17:32:40","guid":{"rendered":"\/?p=847"},"modified":"2007-08-03T14:05:12","modified_gmt":"2007-08-03T22:05:12","slug":"the-biometric-dilemma","status":"publish","type":"post","link":"https:\/\/www.identityblog.com\/?p=847","title":{"rendered":"The Biometric Dilemma"},"content":{"rendered":"<p>Vision researcher <a href=\"http:\/\/www.vast.uccs.edu\/~tboult\/vita.html\">Terrence E. Boult <\/a>has identified what he calls the &#8220;Biometric dilemma&#8221; &#8211; the more we use biometrics the more likely they will be compromised and hence become useless for security.&nbsp;&nbsp;&nbsp;<\/p>\n<p>This is a hugely important&nbsp;observation &#8211; the necessary starting point for all thinking about biometrics.&nbsp;&nbsp;I&#39;d even call it <em>a law<\/em>.<\/p>\n<p>Terrence was responding to a piece by <a href=\"http:\/\/www.seanconvery.com\/weblog\/2007\/08\/01\/more-biometrics-bad-news\/\" class=\"broken_link\">Sean Convery<\/a> that picked up on&nbsp;<a href=\"\/?p=843\">my post&nbsp;<\/a>about reversing biometric templates.&nbsp;&nbsp;Terrence&nbsp;went on to call our attention to&nbsp;more recent work, including&nbsp;some that&nbsp;details the reversibility of fingerprint templates.<!--more--><\/p>\n<p>On the very sober end of things, Terrence cites:<\/p>\n<blockquote><p>A. Ross, J. Shah and A. K. Jain, \u00e2\u20ac\u0153From Template to Image: Reconstructing Fingerprints From Minutiae Points,\u00e2\u20ac\u009d IEEE Transactions on Pattern Analysis and Machine Intelligence, Special Issue on Biometrics, Vol. 29, No. 4, pp. 544-560, April 2007.<\/p>\n<p>Pranab Mohanty, Sudeep Sarkar, Rangachar Kasturi, \u00e2\u20ac\u0153\/From Scores to Face Template: A Model-based Approach\/\u00e2\u20ac\u009d, To appear in IEEE Journal of Pattern Analysis &amp; Machine Intelligence (PAMI)<\/p><\/blockquote>\n<blockquote><p>Pranab Mohanty, Sudeep Sarkar, Rangachar Kasturi, \u00e2\u20ac\u0153\/Privacy &amp;<br \/>\nSecurity Issues Related to Match Scores\/\u00e2\u20ac\u009d, IEEE Workshop on<br \/>\nPrivacy Research In Vision, CVPRW, 2006. *(PDF)<\/p><\/blockquote>\n<p>On what he calls &#8220;a more positive note&#8221;, he says there are many people working on cancelable or \u00e2\u20ac\u0153revocable biometrics\u00e2\u20ac\u009d, as discussed in:<\/p>\n<blockquote><p>&nbsp;<a rel=\"nofollow\" href=\"http:\/\/www.research.ibm.com\/ecvg\/biom\/cancel.html\" onclick=\"javascript:urchinTracker(&#039;\/outbound\/www.research.ibm.com&#039;);\" class=\"broken_link\">http:\/\/www.research.ibm.com\/ecvg\/biom\/cancel.html<\/a> or<\/p>\n<p>T. E. Boult, \u00e2\u20ac\u0153Robust distance measures for face recognition supporting revocable biometric tokens\u00e2\u20ac\u009d, IEEE Conf. on Face and Gesture, April 2006. <a rel=\"nofollow\" href=\"http:\/\/vast.uccs.edu\/~tboult\/vast.uccs.edu\/~tboult\/PAPERS\/Boult-IEEEFG06-preprint.pdf\" onclick=\"javascript:urchinTracker('\/outbound\/vast.uccs.edu');\">http:\/\/vast.uccs.edu\/~tboult\/vast.uccs.edu\/~tboult\/PAPERS\/Boult-IEEEFG06-preprint.pdf<\/a><\/p>\n<p>T.E. Boult, W.J. Scheirer and R. Woodworth, \u00e2\u20ac\u0153Revocable Fingerprint Biotokens: Accuracy and Security Analysis\u00e2\u20ac\u009d, IEEE Conf. on Computer Vision and Pattern Recognition, June 2007.<\/p>\n<p>Cancelable biometric filters for face recognition<br \/>\nSavvides, M.; Vijaya Kumar, B.V.K.; Khosla, P.K.<br \/>\nICPR 2004. 922 &#8211; 925 Vol.3<br \/>\n<a rel=\"nofollow\" href=\"http:\/\/ieeexplore.ieee.org\/Xplore\/login.jsp?url=\/iel5\/9258\/29387\/01334679.pdf\" onclick=\"javascript:urchinTracker('\/outbound\/ieeexplore.ieee.org');\">http:\/\/ieeexplore.ieee.org\/Xplore\/login.jsp?url=\/iel5\/9258\/29387\/01334679.pdf<\/a><\/p><\/blockquote>\n<p>Like Sean, I don&#39;t&nbsp;see how the techniques discussed in the <a href=\"http:\/\/www.research.ibm.com\/ecvg\/biom\/cancel.html\" class=\"broken_link\">IBM paper above <\/a>can be immune to Andy Adler&#39;s attack, in which a large number of photos are put through the same transformation as a target photo and optimized for best match.&nbsp; And if this is the case, how can a biometric really be revocable?&nbsp; But I&#39;m just starting to read this collection of new papers.<\/p>\n<p>BTW, I&nbsp;suggest you check out&nbsp;<a href=\"http:\/\/www.seanconvery.com\/weblog\/\" class=\"broken_link\">Sean Convery&#39;s blog<\/a>.&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The necessary starting point for all thinking about biometrics<\/p>\n","protected":false},"author":68,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[48,17,11],"tags":[],"_links":{"self":[{"href":"https:\/\/www.identityblog.com\/index.php?rest_route=\/wp\/v2\/posts\/847"}],"collection":[{"href":"https:\/\/www.identityblog.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.identityblog.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.identityblog.com\/index.php?rest_route=\/wp\/v2\/users\/68"}],"replies":[{"embeddable":true,"href":"https:\/\/www.identityblog.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=847"}],"version-history":[{"count":0,"href":"https:\/\/www.identityblog.com\/index.php?rest_route=\/wp\/v2\/posts\/847\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.identityblog.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=847"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.identityblog.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=847"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.identityblog.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=847"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}