Call-record analysis is one of the oldest tools used in defense, law-enforcement, and business intelligence. For example, the NSA collected over 1.9 trillion call records between 2001 and 2004 [1]. A call-record database allows both single link (e.g., time, initiation, frequency of a call) and cluster analysis of calls in the temporal, spatial, and frequency domains. It can also indicate overlaps among different clusters, such as those obtained from different investigations, and similarity of clusters, such as those obtained when a group of targets changes their phone numbers but not their communication habits [10, 12].

Private communication detection (PCD) enables an ordinary network user to discover communication patterns (e.g., call time, length, frequency, and initiator) between two or more private parties. Ordinary users have neither eavesdropping capabilities (e.g., the network may employ strong anonymity measures) nor legal authority (e.g., collection of call records---without any voice/data content---requires "national security letters") to collect private-communication records. Analysis of communication patterns between private parties has historically been a powerful tool used by intelligence, military, law-enforcement and business organizations as it can reveal the strength of tie between these parties. In this paper, we show that PCD is possible by ordinary users merely by sending packets to various network end-nodes (e.g., WiFi nodes) and analyzing the timing of their responses. We show that timing side channels, which are caused by distinct resource-contention responses when different applications run in end nodes, enable effective PCD despite network and proxy-generated noise (e.g., jitter, delays). We use a stochastic analysis to demonstrate how PCD exploits indirectly accessible, remote end-node resources, such as WiFi radio channels and computer keyboards in Instant Messaging. Similar analysis enables practical Sybil node detection.

Virtual Ad Hoc Network (VAN) testbed aims at achieving large scale application testing for ad hoc networks by integrating host virtualization and network simulation. Efficient use of storage space is essential for such testbeds. Storage redundancy resulting from duplicated files and application installations across the virtual machines in a large scale testbed (> a few hundred VMs) can be significantly reduced by using storage sharing techniques. Although Content Addressable Storage (CAS) along with Copy-on-write can remove storage redundancy at block-level, it requires hash computation for every write operation that incurs considerable online computation overhead.