The End of Spam?

Stephen DeAngelis

December 11, 2007

If you’re like most people, you have more than one email account and each account is likely to have some kind of spam filter associated with it. John Markoff, writing for the New York Times, reports on the most recent attempt to build a better “trap” [“Spam’s End? Maybe, if Time Allows,” 3 December 2007]. The subject of Markoff’s article is inventor Steven T. Kirsch.

“Twenty-five years ago Steven T. Kirsch built a better mouse. Now he believes he has found a way to create a better trap — for spam, not mice — if he has enough time to finish his project. An M.I.T.-trained engineer, Mr. Kirsch was frustrated by the quality of the first computer mice in 1982, so he set out to improve them by incorporating an optical sensor. Since then he has started four companies, all based on his frustrations with existing products or services. He has made forays into word processing document design, accelerating the Web, and in 1997 Infoseek, his search engine company, was the third ranking company in Web search. In many ways Mr. Kirsch, who is 50 years old, has come to exemplify what distinguishes Silicon Valley — a blend of engineering skills with persistent entrepreneurship.”

One of the characteristics that marks innovative people is an unquenchable curiosity — often expressed in the form of a continual stream of questions about why something doesn’t exist that they see a need for or why something that does exist is built in a certain way. Many innovators carry around a notebook so that they can makes notes when something strikes them as odd or frustrating. I don’t know whether Kirsch does that, but it is apparent that he shares the curious nature that defines creative people. As you might have guessed, Kirsch’s latest frustration is email spam.

“Recently he has taken on the challenge of e-mail spam. This year he founded Abaca, a company with a new approach in the crowded market for stopping junk electronic mail. Abaca claims that it can filter out 99 percent of all spam, and supports the claim with a money-back guarantee. According to the result of an independent survey last February by Opus One, a computer industry consulting firm in Tucson, Ariz., that would be significantly better than the results of six leading spam blockers.”

Kirsch is not necessarily looking to leave a lasting legacy as the man who conquered spam (but that would be quite a legacy). He has already established himself as generous philanthropist — having donated $75 million of his personal fortune to the United Way and other causes. But personal health problems press him to move forward quickly with the challenges he undertakes.

“Abaca has taken on a new urgency for Mr. Kirsch — during the summer, he was discovered to have a rare form of blood cancer, Waldenstrom’s macroglobulinemia, that is found in about 1,500 Americans every year and is considered incurable, although it can be managed beyond the five- to seven-year longevity that new patients are usually told to expect. So far he has shown no effects from the disease, and he said he is intent on applying his engineer’s approach to the problem. … His approach to surviving is outlined in painstaking detail. However, it is listed as the third of his current projects, after ‘Eliminating spam,’ and ‘Who would make the best president?'”

His approach to tackling the spam problem is interesting.

“He has been thinking about the spam problem for a number of years and has several patents covering other approaches, but Mr. Kirsch said he had hit on the idea underlying Abaca — profiling the recipient of e-mail rather than the sender — quite by accident. ‘We were sitting around thinking of ways to obfuscate the description about how our system worked so the spammers would be misdirected,’ he said. ‘So I came up with receiver reputation as something that might sound plausible. Then as I thought about it more and more, the more sense it made to me.’ The approach underlying the Abaca technique is the recognition that the ratio of spam to legitimate e-mail is individually unique. It is also a singular identifier that a spammer cannot manipulate easily. By assessing the combined reputations of the recipients of any individual message, the Abaca system determines the ‘spaminess’ of a particular message. Mr. Kirsch asserts this provides a high degree of accuracy in deciding whether the message is spam. Unlike most of its competitors, he said, Abaca’s technology does not require a training period, is language independent and is faster than many competitors because it does not scan the entire contents of a message to determine whether it is spam.”

One of the techniques that creative people use to search for answers to challenges is forcing themselves to change perspective. For example, if you are planting a garden you can look at the challenge from either the perspective of the planter or the plant. That is what Kirsch did — he looked at the challenge from receiver’s perspective rather than from the spammer’s perspective.

“‘I have to admit it sounds innovative and novel,’ said Sunil Paul, the founder of Brightmail, one of the leading providers of antispam technology, which was sold to Symantec in 1997 for $370 million. At the same time Mr. Paul is dubious about the ability of a stand-alone antispam company in today’s computer security market. ‘Remember BIll Gates’s promise to rid the Internet of spam in a few years?’ he said. ‘That was over seven years ago. Once any of these solutions scale up, though, thousands of other clever, smart people start to work on how to defeat the system.'”

Paul is right, of course, that there are many more spammers looking to defeat Kirsch’s system than programmers Kirsch has working on the challenge. But Kirsch is nevertheless optimistic and he’s an enthusiastic salesman.

“Kirsch insists that Abaca is unlikely to be caught soon. ‘Most people like me get 99.8 percent or so with the current volume of users,’ he said, referring to the percentage of good e-mail he now sees using his system. ‘Our performance gets better as we add more users; our competitors already have scale, and we are way ahead even with just 20,000 users. When we get to scale, our performance should be nearly 100 times better than our closest competitor.’ In February, Opus One tested six antispam products on a stream of 10,000 messages during a 10-day period. Spam catch rates ranged from a high of 97.36 percent to a low of 74.10 percent. ‘At 99.8 percent you miss two out of 1000,’ said Mr. Kirsch. ‘At 95 percent you miss 50 out of 1,000. So other systems give you 25 times as much spam. Who wants that? Nobody we know.’ Opus One has not yet tested the Abaca system. However, the testing group has been briefed by a representative of Abaca.”

The Opus One folks are both intrigued and skeptical Markoff reports. The statistics Markoff uses in his article are about how many spam emails are trapped. There is no indication of how many legitimate messages get caught in the trap. If Abaca’s approach involved a sensor system, the question would be what is the false alarm rate? A sensor system that provides no false alarms is probably missing some actual targets. A spam trap that has a near perfect capture rate is probably capturing some legitimate some legitimate mail as well. In order to make his system work at high levels of effectiveness, Kirsch needs a lot of clients. It will be interesting to see if his obvious zeal can get him a sufficiently large client base to make Abaca a success.