作者: Qiyan Wang , Long Vu , Klara Nahrstedt , Himanshu Khurana
DOI: 10.1109/INFCOM.2010.5462226
关键词:
摘要: Network coding has been shown to be capable of greatly improving quality service in P2P live streaming systems (e.g., IPTV). However, network is vulnerable pollution attacks where malicious nodes inject into the bogus data blocks that are combined with other legitimate at downstream nodes, leading incapability decoding original and substantial degradation performance. In this paper, we propose a novel approach limiting by rapidly identifying nodes. Our scheme can fully satisfy requirements systems, achieves much higher efficiency than previous schemes. Each node our only needs perform several hash computations for an incoming block, incurring very small computational latency. The space overhead added each block 20 bytes. verification information given independent content thus does not need redistributed. simulation results based on real PPLive channel overlays show process takes few seconds even presence large number