A proposal for efficient on-line spam filtering

Sending bulk messages like emails, instant messages, social media messages etc. through an on-line medium to people connected to the medium is known as spamming. Spammers use social-networking sites to instantly spread message, often containing sensitive information, to a wider community of users. Filters for such messages should operate in real time on large volume of data. Also, confidentiality of HAM messages should not be lost. As the channel existing between the service provider and the user in social networking is secure and hence filtering the messages can be only at the service provider end after decryption. This causes considerable overhead at the server side and privacy of legitimate messages are not protected. This paper is a proposal for a novel distributed filtering scheme which can perform SPAM filtering on secure (SSL encrypted) messages without decrypting them. The power of distributed processing solves the filter overhead at the server side and provides the required real time filter without loss of privacy of the HAM messages.