Publications

Refine Results

(Filters Applied) Clear All

Extending the DARPA off-line intrusion detection evaluations

Published in:
DARPA Information Survivability Conf. and Exposition II, 12-14 June 2001, pp. 35-45.

Summary

The 1998 and 1999 DARPA off-line intrusion detection evaluations assessed the performance of intrusion detection systems using realistic background traffic and many examples of realistic attacks. This paper discusses three extensions to these evaluations. First, the Lincoln Adaptable Real-time Information Assurance Testbed (LARIAT) has been developed to simplify intrusion detection development and evaluation. LARIAT allows researchers and operational users to rapidly configure and run real-time intrusion detection and correlation tests with robust background traffic and attacks in their laboratories. Second, "Scenario Datasets" have been crafted to provide examples of multiple component attack scenarios instead of the atomic , attacks as found in past evaluations. Third, extensive analysis of the 1999 evaluation data and results has provided understanding of many attacks, their manifestations, and the features used to detect them. This analysis will be used to develop models of attacks, intrusion detection systems, and intrusion detection system alerts. Successful models could reduce the need for expensive experimentation, allow proof-of-concept analysis and simulations, and form the foundation of a theory of intrusion detection.
READ LESS

Summary

The 1998 and 1999 DARPA off-line intrusion detection evaluations assessed the performance of intrusion detection systems using realistic background traffic and many examples of realistic attacks. This paper discusses three extensions to these evaluations. First, the Lincoln Adaptable Real-time Information Assurance Testbed (LARIAT) has been developed to simplify intrusion detection...

READ MORE

SARA: Survivable Autonomic Response Architecture

Published in:
DARPA Information Survivability Conf. and Exposition II, 12-14 June 2001, pp. 77-88.

Summary

This paper describes the architecture of a system being developed to defend information systems using coordinated autonomic responses. The system will also be used to test the hypothesis that an effective defense against fast, distributed information attacks requires rapid, coordinated, network-wide responses. The core components of the architecture are a run-time infrastructure (RTI), a communication language, a system model, and defensive components. The RTI incorporates a number of innovative design concepts and provides fast, reliable, exploitation-resistant communication and coordination services to the components defending the network, even when challenged by a distributed attack. The architecture can be tailored to provide scalable information assurance defenses for large, geographically distributed, heterogeneous networks with multiple domains, each of which uses different technologies and requires different policies. The architecture can form the basis of a field-deployable system. An initial version is being developed for evaluation in a testbed that will be used to test the autonomic coordination and response hypothesis.
READ LESS

Summary

This paper describes the architecture of a system being developed to defend information systems using coordinated autonomic responses. The system will also be used to test the hypothesis that an effective defense against fast, distributed information attacks requires rapid, coordinated, network-wide responses. The core components of the architecture are a...

READ MORE

Detecting low-profile probes and novel denial-of-service attacks

Summary

Attackers use probing attacks to discover host addresses and services available on each host. Once this information is known, an attacker can then issue a denial-of-service attack against the network, a host, or a service provided by a host. These attacks prevent access to the attacked part of the network. Until recently, only simple, easily defeated mechanisms were used for detecting probe attacks. Attackers defeat these mechanisms by creating stealthy low-profile attacks that include only a few, carefully crafted packets sent over an extended period of time. Furthermore, most mechanisms do not allow intrusion analysts to trade off detection rates for false alarm rates. We present an approach to detect stealthy attacks, an architecture for achieving real-time detections with a confidence measure, and the results of evaluating the system. Since the system outputs confidence values, an analyst can trade false alarm rate against detection rate.
READ LESS

Summary

Attackers use probing attacks to discover host addresses and services available on each host. Once this information is known, an attacker can then issue a denial-of-service attack against the network, a host, or a service provided by a host. These attacks prevent access to the attacked part of the network...

READ MORE

Speaker indexing in large audio databases using anchor models

Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. 1, 7-11 May 2001, pp. 429-432.

Summary

This paper introduces the technique of anchor modeling in the applications of speaker detection and speaker indexing. The anchor modeling algorithm is refined by pruning the number of models needed. The system is applied to the speaker detection problem where its performance is shown to fall short of the state-of-the-art Gaussian Mixture Model with Universal Background Model (GMM-UBM) system. However, it is further shown that its computational efficiency lends itself to speaker indexing for searching large audio databases for desired speakers. Here, excessive computation may prohibit the use of the GMM-UBM recognition system. Finally, the paper presents a method for cascading anchor model and GMM-UBM detectors for speaker indexing. This approach benefits from the efficiency of anchor modeling and high accuracy of GMM-UBM recognition.
READ LESS

Summary

This paper introduces the technique of anchor modeling in the applications of speaker detection and speaker indexing. The anchor modeling algorithm is refined by pruning the number of models needed. The system is applied to the speaker detection problem where its performance is shown to fall short of the state-of-the-art...

READ MORE

Interlingua-based broad-coverage Korean-to-English translation in CCLINC

Published in:
Proc. First Int. Conf. on Human Language Technology, 18-21 March 2001.

Summary

At MIT Lincoln Laboratory, we have been developing a Korean-to-English machine translation system CCLINC (Common Coalition Language System at Lincoln Laboratory). The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame. The key features of the system include: (i) Robust efficient parsing of Korean (a verb final language with overt case markers, relatively free word order, and frequent omissions of arguments). (ii) High quality translation via word sense disambiguation and accurate word order generation of the target language. (iii) Rapid system development and porting to new domains via knowledge-based automated acquisition of grammars. Having been trained on Korean newspaper articles on "missiles" and "chemical biological warfare," the system produces the translation output sufficient for content understanding of the original document.
READ LESS

Summary

At MIT Lincoln Laboratory, we have been developing a Korean-to-English machine translation system CCLINC (Common Coalition Language System at Lincoln Laboratory). The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame. The key features...

READ MORE

The use of dynamic segment scoring for language-independent question answering

Published in:
Proc. 1st Int. Conf. on Human Language Technology Research, HLT, 18-21 March 2001.

Summary

This paper presents a novel language-independent question/answering (Q/A) system based on natural language processing techniques, shallow query understanding, dynamic sliding window techniques, and statistical proximity distribution matching techniques. The performance of the proposed system using the latest Text REtrieval Conference (TREC-8) data was comparable to results reported by the top TREC-8 contenders.
READ LESS

Summary

This paper presents a novel language-independent question/answering (Q/A) system based on natural language processing techniques, shallow query understanding, dynamic sliding window techniques, and statistical proximity distribution matching techniques. The performance of the proposed system using the latest Text REtrieval Conference (TREC-8) data was comparable to results reported by the top...

READ MORE

High Speed Interconnects and Parallel Software Libraries: Enabling Technologies for NVO

Author:
Published in:
Proc. of the Astronomical Society of the Pacific Conf. Series, Vol. 225, 2001, Virtual Observations of the Future, 13-16 June 2000, pp. 297-301.

Summary

The National Virtual Observatory (NVO) will directly or indirectly touch upon all steps in the process of transforming raw observational data into "meaningful" results. These steps include: (1) Acquisition and storage of raw data. (2) Data reduction (i.e. translating raw data into source detections). (3) Aquisition and storage of detected sources. (4) Multi-sensor/multi-temporal data mining of the products of steps (1), (2) and (3). (Not complete.)
READ LESS

Summary

The National Virtual Observatory (NVO) will directly or indirectly touch upon all steps in the process of transforming raw observational data into "meaningful" results. These steps include: (1) Acquisition and storage of raw data. (2) Data reduction (i.e. translating raw data into source detections). (3) Aquisition and storage of detected...

READ MORE

Exploiting VSIPL and OpenMP for Parallel Image Processing

Author:
Published in:
ADASS 2000, Astronomical Data Analysis Software and Systems X, 12-14 November 2000, pp. 209-212.

Summary

VSIPL and OpenMP are two open standards for portable high performance computing. VSIPL delivers optimized single processor performance while OpenMP provides a low overhead mechanism for executing thread based parallelism on shared memory systems. Image processing is one of the main areas where VSIPL and OpenMP can have a large impact. Currently, a large fraction of image processing applications are written in the Interpreted Data Language (IDL) environment. The aim of this work is to demonstrate that the performance benefits of these new standards can be brought to image processing community in a high level manner that is transparent to users. To this end, this talk presents a fast, FFT based algorithm for performing image convolutions. This algorithm has been implemented within the IDL environment using VSIPL (for optimized single processor performance) with added OpenMP directives (for parallelism). This work demonstrates that good parallel speedups are attainable using standards and can be integrated seamlessly into existing user environments.
READ LESS

Summary

VSIPL and OpenMP are two open standards for portable high performance computing. VSIPL delivers optimized single processor performance while OpenMP provides a low overhead mechanism for executing thread based parallelism on shared memory systems. Image processing is one of the main areas where VSIPL and OpenMP can have a large...

READ MORE

The Lincoln speaker recognition system: NIST EVAL2000

Published in:
6th Int. Conf. on Spoken Language, ICSLP, 16-20 October 2000.

Summary

This paper presents an overview of the Lincoln Laboratory systems fielded for the 2000 NIST speaker recognition evaluation (SRE00). In addition to the standard one-speaker detection tasks, this year's evaluation, as in 1999, included multi-speaker spokes dealing with detection, tracking and segmentation. The design approach for the Lincoln system in SRE00 was to develop a set of core one-speaker detection and multi-speaker clustering tools that could be applied to all the tasks. This paper will describe these core systems, how they are applied to the SRE00 tasks and the results they produce. Additionally, a new channel normalization technique known as handset-dependent test-score norm (HTnorm) is introduced.
READ LESS

Summary

This paper presents an overview of the Lincoln Laboratory systems fielded for the 2000 NIST speaker recognition evaluation (SRE00). In addition to the standard one-speaker detection tasks, this year's evaluation, as in 1999, included multi-speaker spokes dealing with detection, tracking and segmentation. The design approach for the Lincoln system in...

READ MORE

Analysis and results of the 1999 DARPA off-line intrusion detection evaluation

Published in:
Proc. Recent Advances in Intrusion Detection, RAID, 2-4 October 2000, pp. 162-182.

Summary

Eight sites participated in the second DARPA off-line intrusion detection evaluation in 1999. Three weeks of training and two weeks of test data were generated on a test bed that emulates a small government site. More than 200 instances of 58 attack types were launched against victim UNIX and Windows NT hosts. False alarm rates were low (less than 10 per day). Best detection was provided by network-based systems for old probe and old denial-of-service (DOS) attacks and by host-based systems for Solaris user-to-root (U2R) attacks. Best over-all performance would have been provided by a combined system that used both host- and network-based intrusion detection. Detection accuracy was poor for previously unseen new, stealthy, and Windows NT attacks. Ten of the 58 attack types were completely missed by all systems. Systems missed attacks because protocols and TCP services were not analyzed at all or to the depth required, because signatures for old attacks did not generalize to new attacks, and because auditing was not available on all hosts.
READ LESS

Summary

Eight sites participated in the second DARPA off-line intrusion detection evaluation in 1999. Three weeks of training and two weeks of test data were generated on a test bed that emulates a small government site. More than 200 instances of 58 attack types were launched against victim UNIX and Windows...

READ MORE