Rahul Simha

A microeconomic approach to optimal resource allocation in distributed computer systems

Decentralized algorithms are examined for optimally distributing a divisible resource in a distributed computer system. To study this problem in a specific context, the problem of optimal file allocation is considered. In this case, the optimization criteria include both the communication cost and average processing delay associated with a file access. The algorithms examined have their origins in the field of mathematical economics. They are shown to have several attractive properties, including their simplicity and distributed nature, the computation of feasible and increasingly better resource allocations as the result of each iteration, and, in the case of file allocation, rapid convergence. Conditions are formally derived under which the algorithms are guaranteed to coverage, and their convergence behavior is additionally examined through simulation. >

Strong minimum energy topology in wireless sensor networks: NP-completeness and heuristics

Wireless sensor networks have recently attracted lots of research effort due to the wide range of applications. These networks must operate for months or years. However, the sensors are powered by battery, which may not be able to be recharged after they are deployed. Thus, energy-aware network management is extremely important. In this paper, we study the following problem: Given a set of sensors in the plane, assign transmit power to each sensor such that the induced topology containing only bidirectional links is strongly connected. This problem is significant in both theory and application. We prove its NP-completeness and propose two heuristics: power assignment based on minimum spanning tree (denoted by MST) and incremental power. We also show that the MST heuristic has a performance ratio of 2. Simulation study indicates that the performance of these two heuristics does not differ very much, but; on average, the incremental power heuristic is always better than MST.

Experimental evaluation of dynamic data allocation strategies in a distributed database with changing workloads

Traditionally, allocation of data in distributed database management systems has been determined by off-line analysis and optimization. This technique works well for static database access patterns, but is often inadequate for frequently changing workloads. In this paper we address how to dynamically reallocate data for partionable distributed databases with changing access patterns. Rather than complicated and expensive optimization algorithms, a simple heuristic is presented and shown, via an implementation study, to improve system throughput by 3 based system. Based on artificial wide area network delays, we show that dynamic reallocation can improve system throughput by a factor of two and a half for wide area networks. We also show that individual site load must be taken into consideration when reallocating data, and provide a simple policy that incorporates load in the reallocation decision.

SAFE-OPS: An approach to embedded software security

The new-found ubiquity of embedded processors in consumer and industrial applications brings with it an intensified focus on security, as a strong level of trust in the system software is crucial to their widespread deployment. The growing area of software protection attempts to address the key steps used by hackers in attacking a software system. In this paper, we introduce a unique approach to embedded software protection that utilizes a hardware/software codesign methodology. Results demonstrate that this framework can be the successful basis for the development of embedded applications that meet a wide range of security and performance requirements.

Analysis of individual packet loss in a finite buffer queue with heterogeneous Markov modulated arrival processes: a study of traffic burstiness and priority packet discarding

The authors consider a queuing system with a finite buffer and multiple heterogeneous arrival streams. They focus on Markov modulated arrival processes with different burstings and investigate the loss of individual arrival streams when the parameters of the heterogeneous arrival streams are varied. The analysis includes both continuous-time and discrete-time treatments of multiplexed heterogeneous Markov modulated arrivals. Loss probabilities are derived for a priority packet discarding scheme. A new characterization of an arrival stream is introduced, referred to as a self-loss, and it is used to qualitatively predict the effects of multiplexing bursty streams with nonbursty streams. The effectiveness of priority packet discarding is also investigated through numerical examples.<<ETX>>

OS support for detecting Trojan circuit attacks

Rapid advances in integrated circuit (IC) development predicted by Moores Law lead to increasingly complex, hard to verify IC designs. Design insiders or adversaries employed at untrusted locations can insert malicious Trojan circuits capable of launching attacks in hardware or supporting software-based attacks. In this paper, we provide a method for detecting Trojan circuit denial-of-service attacks using a simple, verifiable hardware guard external to the complex CPU. The operating system produces liveness checks, embedded in the software clock, to which the guard can respond. We also present a novel method for the OS to detect a hardware-software (HW/SW) Trojan privilege escalation attack by using OS-generated checks to test if the CPU hardware is enforcing memory protection (MP). Our implementation of fine-grained periodic checking of MP enforcement incurs only 2.2% overhead using SPECint 2006.

Transform-based indexing of audio data for multimedia databases

Since the relative proportion of multimedia (video, image and audio) data within databases is expected to increase substantially in the future, keyword-based indexing would be inadequate and efficient content-based query and retrieval are required. The problem of devising content based query, indexing, and retrieval for these newer data types remains an open and challenging problem. While considerable attention has recently been given to image (and, to some extent, video) indexing, much less has been devoted to the problem of indexing its unidimensional counterpart-audio data. The paper proposes content-based indexing schemes for audio data in multimedia databases. The methods are based on transform techniques used in signal processing which transform data from time (or spatial) domain to frequency domain. This offers many advantages such as easy removal of noise, efficient compression and different types of processing. Two algorithms for indexing are presented along with experimental results.

Process-based network decomposition reveals backbone motif structure

A central challenge in systems biology today is to understand the network of interactions among biomolecules and, especially, the organizing principles underlying such networks. Recent analysis of known networks has identified small motifs that occur ubiquitously, suggesting that larger networks might be constructed in the manner of electronic circuits by assembling groups of these smaller modules. Using a unique process-based approach to analyzing such networks, we show for two cell-cycle networks that each of these networks contains a giant backbone motif spanning all the network nodes that provides the main functional response. The backbone is in fact the smallest network capable of providing the desired functionality. Furthermore, the remaining edges in the network form smaller motifs whose role is to confer stability properties rather than provide function. The process-based approach used in the above analysis has additional benefits: It is scalable, analytic (resulting in a single analyzable expression that describes the behavior), and computationally efficient (all possible minimal networks for a biological process can be identified and enumerated).

On sampling controlled stochastic approximation

The authors examine a novel class of stochastic approximation procedures which are based on carefully controlling the number of observations or measurements taken before each computational iteration. This method, referred to as sampling controlled stochastic approximation, has advantages over standard stochastic approximation such as requiring less computation and the ability to handle bias in estimation. The authors address the growth rate required of the number of samples and prove a general convergence theorem for the proposed stochastic approximation method. In addition, they present applications to optimize and also derive a sampling controlled version of the classic Robbins-Munro algorithm. >

Providing secure execution environments with a last line of defense against Trojan circuit attacks

Integrated circuits (ICs) are often produced in foundries that lack effective security controls. In these foundries, sophisticated attackers are able to insert malicious Trojan circuits that are easily hidden in the large, complex circuitry that comprises modern ICs. These so-called Trojan circuits are capable of launching attacks directly in hardware, or, more deviously, can facilitate software attacks. Current defense against Trojan circuits consists of statistical detection techniques to find such circuits before product deployment. The fact that statistical detection can result in false negatives raises the obvious questions: can attacks be detected post-deployment, and is secure execution nonetheless possible using chips with undetected Trojan circuits? In this paper we present the Secure Heartbeat And Dual-Encryption (SHADE) architecture, a compiler-hardware solution for detecting and preventing a subset of Trojan circuit attacks in deployed systems. Two layers of hardware encryption are combined with a heartbeat of off-chip accesses to provide a secure execution environment using untrusted hardware. The SHADE system is designed to complement pre-deployment detection techniques and to add a final, last-chance layer of security.