Sung Je Hong

A real-time communication method for wormhole switching networks

In this paper we propose a real-time communication scheme that can be used in general point-to-point real-time multicomputer systems with wormhole switching. Real-time communication should satisfy the two requirements of predictability and priority handling. Since traditional wormhole switching does not support priority handling which is essential in real-time computing, flit-level preemption is adopted in our wormhole switching. Also, we develop an algorithm to determine the message transmission delay upper bound to predict worst-case message delay. Simulation results show that the delay upper bounds calculated using the proposed algorithm are very close to actual average message transmission delays for messages with high priorities.

A reputation management system in structured peer-to-peer networks

Since there is no method to verify the trustworthiness of shared files in P2P systems, malicious peers can spread untrustworthy files to the system. In order to prevent these untrustworthy files from spreading, we propose an effective reputation management system using peer reputation and file reputation together in DHT-based structured P2P networks. Simulation results show that the proposed system works better in preventing untrustworthy files from spreading than existing systems even in cases of allowing malicious peers to change their identities.

Distance Bounding Protocol for Mutual Authentication

A distance bounding protocol enables one party to determine a practical upper bound on the distance to another party. It is an effective countermeasure against mafia fraud attacks (a.k.a. relay attacks) which do not alter messages between users but only relay messages. The main idea of distance bounding protocols is to repeat fast bit exchanges. One party sends a challenge bit and another party answers with a response bit and vice versa. By measuring the round-trip time between the challenge and the response, an upper bound on the distance between users can be calculated. If messages are relayed, the round-trip time increases and thus mafia fraud attacks can be detected. We introduce an efficient distance bounding protocol for mutual authentication. It enjoys a reduced false acceptance rate under mafia fraud attacks and does not require an extra confirmation message after the fast bit exchange phase.

Processor allocation and task scheduling of matrix chain products on parallel systems

The problem of finding an optimal product sequence for sequential multiplication of a chain of matrices (the matrix chain ordering problem, MCOP) is well-known. We consider the problem of finding an optimal product schedule for evaluating a chain of matrix products on a parallel computer (the matrix chain scheduling problem, MCSP). The difference between MCSP and MCOP is that MCOP pertains to a product sequence for single processor systems and MCSP pertains to a sequence of concurrent matrix products for parallel systems. The approach of parallelizing each matrix product after finding an optimal product sequence for single processor systems does not always guarantee minimum evaluation time on parallel systems since each parallelized matrix product may use processors inefficiently. We introduce a new processor scheduling algorithm for MCSP which reduces the evaluation time of a chain of matrix products on a parallel computer, even at the expense of a slight increase in the total number of operations. Given a chain of n matrices and a matrix product utilizing at most P/k processors in a P-processor system, the proposed algorithm approaches k(n-1)/(n+klog(k)-k) times the performance of parallel evaluation using the optimal sequence found for MCOP. Experiments performed on a Fujitsu AP1000 multicomputer also show that the proposed algorithm significantly decreases the time required to evaluate a chain of matrix products in parallel systems.

Energy-saving design technique achieved by latched pass-transistor adiabatic logic

In recent years, low power circuit design has been an important issue in system on chip (SoC) and VLSI design areas. Adiabatic logics, which dissipate less power than static CMOS logic, have been introduced as a promising new approach in low power circuit design. It is expected that adiabatic logic will be a substitute for static CMOS logic especially for the purpose of low power applications. Despite the proposal of several adiabatic logic families, no research has been done on the technique for replacing CMOS circuits with adiabatic logic. In this paper, we propose a latched pass-transistor adiabatic logic (LPAL) and an energy-saving design scheme for low power applications. LPAL replaces CMOS circuits, providing more energy-efficiency than other forms of adiabatic logic. In simulation, we compared the energy consumption of pass-transistor adiabatic logic (PAL), a good model for conventional adiabatic logics, with that of LPAL. Simulation results show that the LPAL circuit results in power savings of 44% over PAL.

Distance Bounding Protocol with Adjustable False Acceptance Rate

At Eurocrypt 1993, Brands and Chaum introduced distance bounding protocols to defend against mafia fraud attack and distance fraud attack. A distance bounding protocol usually consists of n rounds of a single-bit challenge and a single-bit response, which determines the distance between communicating entities by measuring the round-trip time of signals. Let FAR_M and FAR_D be the false acceptance rate against the mafia fraud attack and the distance fraud attack, respectively. The state-of-the-art distance bounding protocols in terms of the false acceptance rate have either (FAR_M,FAR_D) = ((1/2)ⁿ, (1/2)ⁿ) or (FAR_M,FAR_D) = (4(3/8)ⁿ, (7/8)ⁿ). We introduce a flexible distance bounding protocol whose false acceptance rate (FAR_M,FAR_D) can be chosen from ((1/2)ⁿ, (1/2)ⁿ) to ((1/4)ⁿ, (3/4)ⁿ).

Secure checkpointing

Fault-tolerant computer systems are increasingly being used in such applications as e-commerce, banking, and stock trading, where privacy and integrity of data are as important as the uninterrupted operation of the service provided. While much attention has been paid to the protection of data explicitly communicated over the Internet, there are also other sources of information leakage that must be addressed. This paper addresses one such source of information leakage caused by checkpointing, which is a common method used to provide continued operation in the presence of faults.Checkpointing requires the communication of memory state information, which may contain sensitive data, over the network to a reliable backing store. Although the method of encrypting all of this memory state information can protect the data, such a simplistic method is an overkill that can result in a significant slowdown of the target application. A much more efficient method is to use incremental checkpointing (IC), in which only the modified memory data is saved in stable storage. This paper examines ways to combine the operations required to perform IC with those required to encrypt this memory state data. Our analysis show that the proposed secure checkpointing schemes increase the overhead by 1.57 when compred to conventional checkpointing schemes, which shows the proposed schemes are feasible.

Real-time job scheduling in hypercube systems

In this paper, we present the problem of scheduling real-time jobs in a hypercube system and propose a scheduling algorithm. The goals of the proposed scheduling algorithm are to determine whether all jobs can complete their processing before their fixed deadlines in a hypercube system and to find such a schedule. Each job is associated with a computation time, a deadline, and a dimensional requirement. Determining a schedule such that all jobs meet before their respective fixed deadlines in a hypercube system when preemption is not allowed is an NP-complete problem. Hence, we present a heuristic scheduling algorithm for scheduling non-preemptable real-time jobs in a hypercube system. Finally, we evaluate the proposed algorithm using simulation.

Distance Bounding with Delayed Responses

Distance-bounding protocols enable the establishment of an upper bound on the distance between two communicating parties in such a way that their degree of proximity can be verified. Most of these protocols rely on multi-rounds of single-bit challenge and response. Therefore, in each round, the probability that an adversary will guess the correct response is 1/2. This letter proposes a new method to increase the number of response states of distance-bounding protocols by injecting intentional delays to each round. Our method can reduce the probability of a correct guess from 1/2 to 1/(2k) for each round, where k is the number of different delays, without significant modifications of underlying protocols. Moreover, it can be applied to passive RFID tags, because it requires no special hardware equipment.

Ticket-based fine-grained authorization service in the dynamic VO environment

Virtual Organization (VO) is a collection of users and distributed resources, in which resources are shared by users. Creating VOs is very important task in Grid computing. VOs are dynamically created for some goals and then disappear after the goals are achieved. Conventional authorization architectures for the Grid have been proposed in a single VO environment. However, in reality we often need to handle the situation of several dynamically created VOs. Hence, enough fine-grained authorization methods for all the Grid entities such as resource providers, VO manger, and users do not exist under the dynamic VO environment. In this paper, we propose a TAS architecture to support a fine-grained authorization service in a dynamic VO environment. In contrast to the conventional architecture, TAS architecture uses a ticket that is unforgeable and exchangeable among VO entities for resource control.