Xinli Huang

Building efficient super-peer overlay network for DHT systems

DHT technique has been widely applied in P2P systems because it provides reliable services. However, large overheads are inevitable for maintaining the topology of DHT overlay, which limits its application especially in highly dynamic network environments. This paper proposes a DHT based super-peer overlay network called SPChord in which peer nodes are clustered according to the session time and physical network locality. With an evolving process, SPChord gradually makes DHT overlay stable and reliable. Therefore the high maintaining overheads for DHT overlay are effectively controlled. Experimental results show that the DHT overlay maintaining overheads are reduced dramatically while the overlay stability and the data availability are also greatly improved.

Targeted local immunization in scale-free peer-to-peer networks

The power-law node degree distributions of peer-to-peer overlay networks make them extremely robust to random failures whereas highly vulnerable under intentional targeted attacks. To enhance attack survivability of these networks, DeepCure, a novel heuristic immunization strategy, is proposed to conduct decentralized but targeted immunization. Different from existing strategies, DeepCure identifies immunization targets as not only the highly-connected nodes but also the nodes with high availability and/or high link load, with the aim of injecting immunization information into just right targets to cure. To better trade off the cost and the efficiency, DeepCure deliberately select these targets from 2-local neighborhood, as well as topologically-remote but semantically-close friends if needed. To remedy the weakness of existing strategies in case of sudden epidemic outbreak, DeepCure is also coupled with a local-hub oriented rate throttling mechanism to enforce proactive rate control. Extensive simulation results show that DeepCure outperforms its competitors, producing an arresting increase of the network attack tolerance, at a lower price of eliminating viruses or malicious attacks.

ToA^3: Beyond the Limit of Unstructured P2P Networks

A major limitation of current unstructured peer-to-peer (P2P) networks lies in the inefficiency of search, which results in fatal scalability problems. In this paper, ToA3, a novel P2P file-sharing system, is proposed to tackle such a limitation. The key idea of ToA3 is to generate an overlay topology with DESIRABLE properties, adapt peers towards BETTER neighbors dynamically, and direct queries to RIGHT next nodes with as few duplicated messages as possible. To achieve this goal, ToA3 introduces several innovative techniques such as: (a) a dynamic topology adaptation algorithm with self-sustaining power-law degree distributions, (b) a simply but efficient utilization of peer-to-peer network heterogeneity, (c) a proper implementation of the underlying-network-awareness, and (d) Smart Search-a biased search algorithm used in ToA3. Extensive simulations substantiate that our techniques significantly improve the search performance and reduce the network load dramatically

Enhancing Attack Survivability of Gnutella-like P2P Networks by Targeted Immunization Scheme

Gnutella-like Peer-to-Peer Networks, due to their extreme connectivity fluctuations, are highly robust against random failures. However, such error tolerance comes at a high price of attack survivability. In this paper, to enhance such attack survivability, we propose a new formulation used for defense against deliberately attacks based on two leading concepts: cost and load. The cost measures how expensive it is to cure an attacked or infected node, and the load measures how important a link between two nodes is when propagating attacks or updating immunization information reversely. The combination of these factors leads us to introduce the concept of optimal targeted immunization, which formalizes the ideas of minimizing the risk of epidemic outbreaks in these networks. Using this analysis framework, we then devise a novel efficient targeted immunization scheme. The simulation results under a realistic Gnutella network show that our immunization scheme outperforms other existing methods, producing an arresting increase of the network attack tolerance at a lower price of eliminating malicious attacks.

TAON: A Topology-Oriented Active Overlay Network Protocol

Built upon overlay topologies, Peer-to-Peer (P2P) networks behave in an ad-hoc way, conduct application-layer routing, enable user-customized decentralized resources sharing, and thus can be taken as an emerging representative of Active Networks. An important problem in current unstructured P2P networks is that, however, existing searching mechanisms do not scale well because they are either based on the idea of flooding the network with queries or because they know very little about the nature of the network topology. In this paper, we propose the Topology-oriented Active Overlay Network (TAON) which is an efficient, scalable yet simple protocol for improving decentralized resources sharing in P2P networks. TAON consists of three novel components: a Desirable Topology Construction and Adaptation algorithm to guide the evolution of the overlay topology towards a small-world-like graph, a Semantic-based Neighbor Selection Scheme to conduct an online neighbor ranking, and a Topology-aware Intelligent Search mechanism to forward incoming queries to deliberately selected neighbors. We deploy and compare TAON with a number of other distributed search techniques over static and dynamic environments, and the results indicate that TAON outperforms its competitors by achieving higher recall rate while using much less network resources, in both of the above environments.

Attack vulnerability of peer-to-peer networks and cost-effective immunization

Currently, great efforts on network security are being made to concern software protection and prevention of loopholes, rather than the network topology. In this paper, we present a detailed and in-depth study on the response of peer-to-peer (P2P) networks subject to attacks, and investigate how to improve their attack survivability with a viewpoint of topological properties. We first, by extensive simulations, examine the attack vulnerability of P2P networks and find that these networks are extremely robust to random attacks whereas highly vulnerable under intentional targeted attacks. Based on these findings, we then develop a novel framework better characterizing the immunization of Gnutella-like P2P networks by taking into account the cost of curing infected peers. Finally, we propose a unique defense policy against intentional attacks and verify its performance merits via comprehensive experiments.

Exploring small-world-like topologies via splitprober: turning power laws into an advantage in unstructured overlays

Recent unstructured Peer-to-Peer systems, represented by Gnutella and Freenet, offer an administration-free and fault-tolerant application-level overlay network. While elegant from a theoretical perspective, these systems have some serious disadvantages. First, due to knowing very little about the nature of the network topology, the search algorithms operating on these networks result in fatal scaling problems. Second, these systems rely on application-level routing, which may be inefficient with respect to network delays and bandwidth consumption. In this paper, we propose a novel search algorithm, called SplitProber, to explore the small-world-like topologies of these networks efficiently and scalablely, by turning the power-law degree distributions in these networks to an advantage, and by making discriminative use of nodes according to their different roles in the network. As a result, we are able to reconcile the conflict of remedying the mismatch between the overlay topology and its projection on the underlying physical network, while at the same time navigating these networks with a guaranteed high efficiency and using only local knowledge as cues. Our simulation results indicate that the proposed algorithm outperforms several other well-known methods with significant performance gains.

GToS: examining the role of overlay topology on system performance improvement

Gnutella’s notoriously poor scaling led some to propose distributed hash table solutions to the wide-area file search problem. Contrary to that trend, in this paper, we advocate retaining Gnutella’s simplicity while proposing GToS, a G nutella-like T opology- o riented S earch protocol for high-performance distributed file sharing, by examining the role of overlay topology on system performance improvement. Building upon prior research [10], we propose several modifications as enhancements and then refine these novel ideas, with the aim of trying to remedy the “mismatch” between the logical overlay topology and its projection on the underlying network. We test our design through extensive simulations and the results show a significant system performance improvement.

On protection of threatened unstructured overlays: an economic defense model and its applications

The presence of power-law connectivity distributions and small-world characteristics in current unstructured overlay networks, so useful to speed up the communication process, ironically, also exposes some fatal topological weaknesses, e.g., being extremely vulnerable under intentional targeted intrusions, which seriously reduces their intrusion survivability. As a remedy, we in this paper propose a novel generalized and practical analytical formulation called Economic Defense Model, to characterize the intrusion spreading in these networks and provide guidelines for controlling the epidemic outbreaks. Based on (but much different from) currently existing methods, our model focuses on two key concepts of efficiency and cost, by giving deep insight into the role of topological properties, like the scale free behaviors, the small-world-like phenomena, the statistical significance of both nodes and links during dynamic topology evolution over time. Moreover, we propose a novel economic defense strategy and then perform a case study to examine how efficiency and economy principles combine up to shape the epidemics and immunization in these overlays.

Towards Efficient and Scalable Searches for Mass-Market, Decentralized File-Sharing Applications

Unstructured Peer-to-Peer networks support uncoupled data placements, elaborate semantic queries and highly dynamic scenario. These properties make such systems extraordinary suitable for applications of mass-market decentralized file sharing, which is still the most dominant application currently in use on current P2P-powered systems. In this paper, we propose SSplus, a novel search algorithm extended from our previously developed Smart Search algorithm, focusing on improving the search efficiency and the network utilization in unstructured P2P file-sharing systems. We achieve these goals by introducing several novel techniques below as enhancements: (a) Load Balancing based on Free Availability, (b) Intelligent 2-Level Replication, and (c) Resources Booking and Reservation. Extensive simulations under realistic conditions substantiate significant performance gains of SSplus, compared with the original Smart Search algorithm.