PARASITIC COMPUTING

The net is a fertile place where new ideas/products surface quite often. We have already come across many innovative ideas such as Peer-to-Peer file sharing, distributed computing etc. Parasitic computing is a new in this category. Reliable communication on the Internet is guaranteed by a standard set of protocols, used by all computers. The Notre Dame computer scientist showed that these protocols could be exploited to compute with the communication infrastructure, transforming the Internet into a distributed computer in which servers unwittingly perform computation on behalf of a remote node.

In this model, known as “parasitic computing”, one machine forces target computers to solve a piece of a complex computational problem merely by engaging them in standard communication. Consequently, the target computers are unaware that they have performed computation for the benefit of a commanding node. As experimental evidence of the principle of parasitic computing, the scientists harnessed the power of several web servers across the globe, which–unknown to them–work together to solve an NP complete problem.

Sending a message through the Internet is a sophisticated process regulated by layers of complex protocols. For example, when a user selects a URL (uniform resource locator), requesting a web page, the browser opens a transmission control protocol (TCP) connection to a web server. It then issues a hyper-text transmission protocol (HTTP) request over the TCP connection. The TCP message is carried via the Internet protocol (IP), which might break the message into several packages, which navigate independently through

numerous routers between source and destination. When an HTTP request reaches its target web server, a response is returned via the same TCP connection to the user's browser. The original message is reconstructed through a series of consecutive steps, involving IP and TCP; it is finally interpreted at the HTTP level, eliciting the appropriate response (such as sending the requested web page). Thus, even a seemingly simple request for a web page involves a significant amount of computation in the network and at the computers at the end points.

In essence, a `parasitic computer' is a realization of an abstract machine for a distributed computer that is built upon standard Internet communication protocols. We use a parasitic computer to solve the well known NP-complete satisfiability problem, by engaging various web servers physically located in North America, Europe, and Asia, each of which unknowingly participated in the experiment. Like the SETI@home project, parasitic computing decomposes a complex problem into computations that can be evaluated independently and solved by computers connected to the Internet; unlike the SETI project, however, it does so without the knowledge of the participating servers. Unlike `cracking' (breaking into a computer) or computer viruses, however, parasitic computing does not compromise the security of the targeted servers, and accesses only those parts of the servers that have been made explicitly available for Internet communication.