{"51421":{"#nid":"51421","#data":{"type":"news","title":"GTISC and ARC Researchers Collaborate to Develop Next-Generation Spam Filters","body":[{"value":"\u003Cp\u003EGraduate student Anirudh Ramachandran\u0027s work on filtering spam using\u003Cbr \/\u003E\nnetwork-level properties will appear at the ACM Conference on Computer\u003Cbr \/\u003E\nand Communications Security (CCS), ACM\u0027s top security conference, at\u003Cbr \/\u003E\nthe end of October.\u00a0 Ramachandran and his advisor, Assistant Professor\u003Cbr \/\u003E\nNick Feamster, have been working with Professor Santosh Vempala to\u003Cbr \/\u003E\ndevelop next-generation spam filtering techniques.\u003C\/p\u003E\n\u003Cp\u003ESpam is becoming increasingly virulent as it makes use of images and\u003Cbr \/\u003E\nPDFs to evade content-based filters.\u00a0 To make matters worse, spammers\u003Cbr \/\u003E\nare sending spam from \u0022fresh\u0022 machines every day, which makes it\u003Cbr \/\u003E\ndifficult to maintain static blacklists of known bad senders.\u00a0 \u003C\/p\u003E\n\u003Cp\u003ETo get a step ahead, the researchers have taken a different approach:\u003Cbr \/\u003E\n\u003Cbr \/\u003E\nrather than filtering spam based on content or an ephemeral identity of\u003Cbr \/\u003E\nthe sender (e.g., an IP address), the researchers have invented a new\u003Cbr \/\u003E\ntechnique called \u0022behavioral blacklisting\u0022.\u00a0 Behavioral blacklisting\u003Cbr \/\u003E\naims to learn and \u0022fingerprint\u0022 spammers\u0027 sending patterns---for\u003Cbr \/\u003E\nexample, the set of recipients a particular sender is targeting---and\u003Cbr \/\u003E\nblacklist senders based on their sending behavior, rather than a fixed\u003Cbr \/\u003E\nidentity.\u003C\/p\u003E\n\u003Cp\u003EThe researchers developed their first behavioral blacklisting technique\u003Cbr \/\u003E\nby applying Professor Vempala\u0027s novel spectral clustering algorithms,\u003Cbr \/\u003E\nwhich have also successfully been applied to other areas (e.g., Web\u003Cbr \/\u003E\nsearch).\u003C\/p\u003E\n\u003Cp\u003E\u003Ca href=\u0022http:\/\/www.cc.gatech.edu\/~avr\/publications\/ccs07.pdf\u0022\u003EYou can read the paper here.\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp\u003E\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EGraduate student Anirudh Ramachandran\u0027s work on filtering spam using network-level properties will appear at the ACM Conference on Computer and Communications Security (CCS), ACM\u0027s top security conference, at the end of October.\u003Cbr \/\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":"","uid":"27154","created_gmt":"2010-02-09 21:43:54","changed_gmt":"2016-10-08 03:04:49","author":"Louise Russo","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2007-08-24T00:00:00-04:00","iso_date":"2007-08-24T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"groups":[{"id":"47223","name":"College of Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}