Publications

Refine Results

(Filters Applied) Clear All

Artificial intelligence: short history, present developments, and future outlook, final report

Summary

The Director's Office at MIT Lincoln Laboratory (MIT LL) requested a comprehensive study on artificial intelligence (AI) focusing on present applications and future science and technology (S&T) opportunities in the Cyber Security and Information Sciences Division (Division 5). This report elaborates on the main results from the study. Since the AI field is evolving so rapidly, the study scope was to look at the recent past and ongoing developments to lead to a set of findings and recommendations. It was important to begin with a short AI history and a lay-of-the-land on representative developments across the Department of Defense (DoD), intelligence communities (IC), and Homeland Security. These areas are addressed in more detail within the report. A main deliverable from the study was to formulate an end-to-end AI canonical architecture that was suitable for a range of applications. The AI canonical architecture, formulated in the study, serves as the guiding framework for all the sections in this report. Even though the study primarily focused on cyber security and information sciences, the enabling technologies are broadly applicable to many other areas. Therefore, we dedicate a full section on enabling technologies in Section 3. The discussion on enabling technologies helps the reader clarify the distinction among AI, machine learning algorithms, and specific techniques to make an end-to-end AI system viable. In order to understand what is the lay-of-the-land in AI, study participants performed a fairly wide reach within MIT LL and external to the Laboratory (government, commercial companies, defense industrial base, peers, academia, and AI centers). In addition to the study participants (shown in the next section under acknowledgements), we also assembled an internal review team (IRT). The IRT was extremely helpful in providing feedback and in helping with the formulation of the study briefings, as we transitioned from datagathering mode to the study synthesis. The format followed throughout the study was to highlight relevant content that substantiates the study findings, and identify a set of recommendations. An important finding is the significant AI investment by the so-called "big 6" commercial companies. These major commercial companies are Google, Amazon, Facebook, Microsoft, Apple, and IBM. They dominate in the AI ecosystem research and development (R&D) investments within the U.S. According to a recent McKinsey Global Institute report, cumulative R&D investment in AI amounts to about $30 billion per year. This amount is substantially higher than the R&D investment within the DoD, IC, and Homeland Security. Therefore, the DoD will need to be very strategic about investing where needed, while at the same time leveraging the technologies already developed and available from a wide range of commercial applications. As we will discuss in Section 1 as part of the AI history, MIT LL has been instrumental in developing advanced AI capabilities. For example, MIT LL has a long history in the development of human language technologies (HLT) by successfully applying machine learning algorithms to difficult problems in speech recognition, machine translation, and speech understanding. Section 4 elaborates on prior applications of these technologies, as well as newer applications in the context of multi-modalities (e.g., speech, text, images, and video). An end-to-end AI system is very well suited to enhancing the capabilities of human language analysis. Section 5 discusses AI's nascent role in cyber security. There have been cases where AI has already provided important benefits. However, much more research is needed in both the application of AI to cyber security and the associated vulnerability to the so-called adversarial AI. Adversarial AI is an area very critical to the DoD, IC, and Homeland Security, where malicious adversaries can disrupt AI systems and make them untrusted in operational environments. This report concludes with specific recommendations by formulating the way forward for Division 5 and a discussion of S&T challenges and opportunities. The S&T challenges and opportunities are centered on the key elements of the AI canonical architecture to strengthen the AI capabilities across the DoD, IC, and Homeland Security in support of national security.
READ LESS

Summary

The Director's Office at MIT Lincoln Laboratory (MIT LL) requested a comprehensive study on artificial intelligence (AI) focusing on present applications and future science and technology (S&T) opportunities in the Cyber Security and Information Sciences Division (Division 5). This report elaborates on the main results from the study. Since the...

READ MORE

GraphChallenge.org: raising the bar on graph analytic performance

Summary

The rise of graph analytic systems has created a need for new ways to measure and compare the capabilities of graph processing systems. The MIT/Amazon/IEEE Graph Challenge has been developed to provide a well-defined community venue for stimulating research and highlighting innovations in graph analysis software, hardware, algorithms, and systems. GraphChallenge.org provides a wide range of preparsed graph data sets, graph generators, mathematically defined graph algorithms, example serial implementations in a variety of languages, and specific metrics for measuring performance. Graph Challenge 2017 received 22 submissions by 111 authors from 36 organizations. The submissions highlighted graph analytic innovations in hardware, software, algorithms, systems, and visualization. These submissions produced many comparable performance measurements that can be used for assessing the current state of the art of the field. There were numerous submissions that implemented the triangle counting challenge and resulted in over 350 distinct measurements. Analysis of these submissions show that their execution time is a strong function of the number of edges in the graph, Ne, and is typically proportional to N4=3 e for large values of Ne. Combining the model fits of the submissions presents a picture of the current state of the art of graph analysis, which is typically 108 edges processed per second for graphs with 108 edges. These results are 30 times faster than serial implementations commonly used by many graph analysts and underscore the importance of making these performance benefits available to the broader community. Graph Challenge provides a clear picture of current graph analysis systems and underscores the need for new innovations to achieve high performance on very large graphs.
READ LESS

Summary

The rise of graph analytic systems has created a need for new ways to measure and compare the capabilities of graph processing systems. The MIT/Amazon/IEEE Graph Challenge has been developed to provide a well-defined community venue for stimulating research and highlighting innovations in graph analysis software, hardware, algorithms, and systems...

READ MORE

Detecting intracranial hemorrhage with deep learning

Published in:
40th Int. Conf. of the IEEE Engineering in Medicine and Biology Society, EMBC, 17-21 July 2018.

Summary

Initial results are reported on automated detection of intracranial hemorrhage from CT, which would be valuable in a computer-aided diagnosis system to help the radiologist detect subtle hemorrhages. Previous work has taken a classic approach involving multiple steps of alignment, image processing, image corrections, handcrafted feature extraction, and classification. Our current work instead uses a deep convolutional neural network to simultaneously learn features and classification, eliminating the multiple hand-tuned steps. Performance is improved by computing the mean output for rotations of the input image. Postprocessing is additionally applied to the CNN output to significantly improve specificity. The database consists of 134 CT cases (4,300 images), divided into 60, 5, and 69 cases for training, validation, and test. Each case typically includes multiple hemorrhages. Performance on the test set was 81% sensitivity per lesion (34/42 lesions) and 98% specificity per case (45/46 cases). The sensitivity is comparable to previous results (on different datasets), but with a significantly higher specificity. In addition, insights are shared to improve performance as the database is expanded.
READ LESS

Summary

Initial results are reported on automated detection of intracranial hemorrhage from CT, which would be valuable in a computer-aided diagnosis system to help the radiologist detect subtle hemorrhages. Previous work has taken a classic approach involving multiple steps of alignment, image processing, image corrections, handcrafted feature extraction, and classification. Our...

READ MORE

Adversarial co-evolution of attack and defense in a segmented computer network environment

Published in:
Proc. Genetic and Evolutionary Computation Conf. Companion, GECCO 2018, 15-19 July 2018, pp. 1648-1655.

Summary

In computer security, guidance is slim on how to prioritize or configure the many available defensive measures, when guidance is available at all. We show how a competitive co-evolutionary algorithm framework can identify defensive configurations that are effective against a range of attackers. We consider network segmentation, a widely recommended defensive strategy, deployed against the threat of serial network security attacks that delay the mission of the network's operator. We employ a simulation model to investigate the effectiveness over time of different defensive strategies against different attack strategies. For a set of four network topologies, we generate strong availability attack patterns that were not identified a priori. Then, by combining the simulation with a coevolutionary algorithm to explore the adversaries' action spaces, we identify effective configurations that minimize mission delay when facing the attacks. The novel application of co-evolutionary computation to enterprise network security represents a step toward course-of-action determination that is robust to responses by intelligent adversaries.
READ LESS

Summary

In computer security, guidance is slim on how to prioritize or configure the many available defensive measures, when guidance is available at all. We show how a competitive co-evolutionary algorithm framework can identify defensive configurations that are effective against a range of attackers. We consider network segmentation, a widely recommended...

READ MORE

Influence estimation on social media networks using causal inference

Published in:
Proc. IEEE Statistical Signal Processing (SSP) Workshop, 10-13 June 2018.

Summary

Estimating influence on social media networks is an important practical and theoretical problem, especially because this new medium is widely exploited as a platform for disinformation and propaganda. This paper introduces a novel approach to influence estimation on social media networks and applies it to the real-world problem of characterizing active influence operations on Twitter during the 2017 French presidential elections. The new influence estimation approach attributes impact by accounting for narrative propagation over the network using a network causal inference framework applied to data arising from graph sampling and filtering. This causal framework infers the difference in outcome as a function of exposure, in contrast to existing approaches that attribute impact to activity volume or topological features, which do not explicitly measure nor necessarily indicate actual network influence. Cramér-Rao estimation bounds are derived for parameter estimation as a step in the causal analysis, and used to achieve geometrical insight on the causal inference problem. The ability to infer high causal influence is demonstrated on real-world social media accounts that are later independently confirmed to be either directly affiliated or correlated with foreign influence operations using evidence supplied by the U.S. Congress and journalistic reports.
READ LESS

Summary

Estimating influence on social media networks is an important practical and theoretical problem, especially because this new medium is widely exploited as a platform for disinformation and propaganda. This paper introduces a novel approach to influence estimation on social media networks and applies it to the real-world problem of characterizing...

READ MORE

Hybrid mixed-membership blockmodel for inference on realistic network interactions

Published in:
IEEE Trans. Netw. Sci. Eng., Vol. 6, No. 3, July-Sept. 2019.

Summary

This work proposes novel hybrid mixed-membership blockmodels (HMMB) that integrate three canonical network models to capture the characteristics of real-world interactions: community structure with mixed-membership, power-law-distributed node degrees, and sparsity. This hybrid model provides the capacity needed for realism, enabling control and inference on individual attributes of interest such as mixed-membership and popularity. A rigorous inference procedure is developed for estimating the parameters of this model through iterative Bayesian updates, with targeted initialization to improve identifiability. For the estimation of mixed-membership parameters, the Cramer-Rao bound is derived by quantifying the information content in terms of the Fisher information matrix. The effectiveness of the proposed inference is demonstrated in simulations where the estimates achieve covariances close to the Cramer-Rao bound while maintaining good truth coverage. We illustrate the utility of the proposed model and inference procedure in the application of detecting a community from a few cue nodes, where success depends on accurately estimating the mixed-memberships. Performance evaluations on both simulated and real-world data show that inference with HMMB is able to recover mixed-memberships in the presence of challenging community overlap, leading to significantly improved detection performance over algorithms based on network modularity and simpler models.
READ LESS

Summary

This work proposes novel hybrid mixed-membership blockmodels (HMMB) that integrate three canonical network models to capture the characteristics of real-world interactions: community structure with mixed-membership, power-law-distributed node degrees, and sparsity. This hybrid model provides the capacity needed for realism, enabling control and inference on individual attributes of interest such as...

READ MORE

Trust and performance in human-AI systems for multi-domain command and control

Summary

Command and Control is one of the core tenants of joint military operations, however, the nature of modern security threats, the democratization of technology globally, and the speed and scope of information flows are stressing traditional operational paradigms, necessitating a fundamental shift to better concurrently integrate and operate across multiple physical and virtual domains. In this paper, we aim to address these challenges through the proposition of three concepts that will guide the creation of integrated human-AI Command and Control systems, inspired by recent advances and successes within the commercial sector and academia. The first concept is a framework for integration of AI capabilities into the enterprise that optimizes trust and performance within the workforce. The second is an approach for facilitating multi-domain operations though realtime creation of multi-organization multi-domain task teams by dynamic management of information abstraction, teaming, and risk control. The third is a new paradigm for multi-level data security and multi-organization data sharing that will be a key enabler of joint and coalition multi-domain operation in the future. Lastly, we propose a set of recommendations towards the research, development, and instantiation of these transformative advances in Command and Control capability.
READ LESS

Summary

Command and Control is one of the core tenants of joint military operations, however, the nature of modern security threats, the democratization of technology globally, and the speed and scope of information flows are stressing traditional operational paradigms, necessitating a fundamental shift to better concurrently integrate and operate across multiple...

READ MORE

XLab: early indications & warning from open source data with application to biological threat

Published in:
Proc. 51st Hawaii Int. Conf. on System Sciences, HICSS 2018, pp. 944-953.

Summary

XLab is an early warning system that addresses a broad range of national security threats using a flexible, rapidly reconfigurable architecture. XLab enables intelligence analysts to visualize, explore, and query a knowledge base constructed from multiple data sources, guided by subject matter expertise codified in threat model graphs. This paper describes a novel system prototype that addresses threats arising from biological weapons of mass destruction. The prototype applies knowledge extraction analytics—including link estimation, entity disambiguation, and event detection—to build a knowledge base of 40 million entities and 140 million relationships from open sources. Exact and inexact subgraph matching analytics enable analysts to search the knowledge base for instances of modeled threats. The paper introduces new methods for inexact matching that accommodate threat models with temporal and geospatial patterns. System performance is demonstrated using several simplified threat models and an embedded scenario.
READ LESS

Summary

XLab is an early warning system that addresses a broad range of national security threats using a flexible, rapidly reconfigurable architecture. XLab enables intelligence analysts to visualize, explore, and query a knowledge base constructed from multiple data sources, guided by subject matter expertise codified in threat model graphs. This paper...

READ MORE

Streaming graph challenge: stochastic block partition

Summary

An important objective for analyzing real-world graphs is to achieve scalable performance on large, streaming graphs. A challenging and relevant example is the graph partition problem. As a combinatorial problem, graph partition is NP-hard, but existing relaxation methods provide reasonable approximate solutions that can be scaled for large graphs. Competitive benchmarks and challenges have proven to be an effective means to advance state-of-the-art performance and foster community collaboration. This paper describes a graph partition challenge with a baseline partition algorithm of sub-quadratic complexity. The algorithm employs rigorous Bayesian inferential methods based on a statistical model that captures characteristics of the real-world graphs. This strong foundation enables the algorithm to address limitations of well-known graph partition approaches such as modularity maximization. This paper describes various aspects of the challenge including: (1) the data sets and streaming graph generator, (2) the baseline partition algorithm with pseudocode, (3) an argument for the correctness of parallelizing the Bayesian inference, (4) different parallel computation strategies such as node-based parallelism and matrix-based parallelism, (5) evaluation metrics for partition correctness and computational requirements, (6) preliminary timing of a Python-based demonstration code and the open source C++ code, and (7) considerations for partitioning the graph in streaming fashion. Data sets and source code for the algorithm as well as metrics, with detailed documentation are available at GraphChallenge.org.
READ LESS

Summary

An important objective for analyzing real-world graphs is to achieve scalable performance on large, streaming graphs. A challenging and relevant example is the graph partition problem. As a combinatorial problem, graph partition is NP-hard, but existing relaxation methods provide reasonable approximate solutions that can be scaled for large graphs. Competitive...

READ MORE

Static graph challenge: subgraph isomorphism

Summary

The rise of graph analytic systems has created a need for ways to measure and compare the capabilities of these systems. Graph analytics present unique scalability difficulties. The machine learning, high performance computing, and visual analytics communities have wrestled with these difficulties for decades and developed methodologies for creating challenges to move these communities forward. The proposed Subgraph Isomorphism Graph Challenge draws upon prior challenges from machine learning, high performance computing, and visual analytics to create a graph challenge that is reflective of many real-world graph analytics processing systems. The Subgraph Isomorphism Graph Challenge is a holistic specification with multiple integrated kernels that can be run together or independently. Each kernel is well defined mathematically and can be implemented in any programming environment. Subgraph isomorphism is amenable to both vertex-centric implementations and array-based implementations (e.g., using the Graph-BLAS.org standard). The computations are simple enough that performance predictions can be made based on simple computing hardware models. The surrounding kernels provide the context for each kernel that allows rigorous definition of both the input and the output for each kernel. Furthermore, since the proposed graph challenge is scalable in both problem size and hardware, it can be used to measure and quantitatively compare a wide range of present day and future systems. Serial implementations in C++, Python, Python with Pandas, Matlab, Octave, and Julia have been implemented and their single threaded performance have been measured. Specifications, data, and software are publicly available at GraphChallenge.org.
READ LESS

Summary

The rise of graph analytic systems has created a need for ways to measure and compare the capabilities of these systems. Graph analytics present unique scalability difficulties. The machine learning, high performance computing, and visual analytics communities have wrestled with these difficulties for decades and developed methodologies for creating challenges...

READ MORE