Secure Packet Transmission Against Pilot Spoofing and Phishing Attack

The pilot spoofing attack is one kind of active eavesdropping activities conducted by a malicious user during the channel training phase. By transmitting the identical pilot (training) signals as those of the legal users, such an attack is able to manipulate the channel estimation outcome, which may result in a larger channel rate for the adversary but a smaller channel rate for the legitimate receiver. With the intention of detecting the pilot spoofing attack and minimising its damages, we design a two-way training-based scheme. The effective detector exploits the intrusive component created by the adversary, followed by a secure beam forming-assisted data transmission. In addition to the solid detection performance, this scheme is also capable of obtaining the estimations of both legitimate and illegitimate channels, which allows the users to achieve secure communication in the presence of pilot spoofing attack. Phishing attacks were highly concentrated in targeting at a few major Websites. In this project, the machine learning based phishing detection using only lexical and domain features, which are available even when the phishing Web Pages are inaccessible. We then select an optimal set of features in our phishing detector, which has achieved a detection rate better than 98%, with a false positive rate of 0.64% or less. The detector is still effective when the distribution of phishing URLs changes.