Heal Gossip: A Secure Overlay for Unstructured P2P Networks
Anubhava Srivastava · International Journal on Data Science and Technology · 2016
Gossip-based protocols are an e cient mechanism for man-aging pure unstructured peer-to-peer (P2P) networks. Such protocols are Newscast, Cyclone, Lbpcast, etc. They have overcome from several di culties of such P2P random overlay connection. Such difficulties are randomness, high churn rate, very large unstructured distributed net-work, etc. But the performance of all gossip-based protocols have been completely vanished by presence of few malicious nodes. Since, non-detectable messages and behaviour of attackers are not leave them se-cure. These malicious nodes divide the overlay into several isolated clusters such as in Hub Attack or may be engaged non-malicious nodes in such a way that they are denying actual work such as in Denial of Ser-vice (DoS) Attacks. For securing unstructured P2P networks, there are some existing security protocols such as Secure Peer Sampling (SPSS), TooLate, S-Gossip etc. They are able to identify the malicious nodes and restrict them from gossiping. But restricting some malicious nodes on each node is not sufficient the security purpose of such epidemic over-lays. Especially in completely distributed networks, the malicious nodes may affect other non-malicious nodes although they have been already captured and restricted for gossip on others. In this regards, a new gossip mechanism is proposed, named HealGos-sip. It uses an additional property to inform captured malicious nodes on a node to all its neighbours. This process helps to identify and re-strict malicious nodes faster than other security mechanism. The propose mechanism relief the non-malicious nodes from the group of malicious nodes while performing detecting process. Hence, the propose protocol reduces the communication overhead as well as paralyses almost all malicious nodes within the network. For confusing among malicious and non-malicious nodes while detecting, a new variant of Hub attack is pro-posed and is called Hide and Seek (HnS) attack. It is able to miss-lead existing security protocols regarding the restriction of malicious nodes from gossip.