Smart Information Flow Technologies - artificial intelligence

Characterizing Human Activities for Cancer Health Awareness

hborck — Thu, 09 Jun 2022 18:33:40 +0000

Background
Automated analysis of physical activity (such as 'walking', 'squats', or 'jumping jacks') and performance from video is lacking in the clinical, home monitoring and public health applications domain. Performance refers to quantitative measures of function such as walking speed or timing of a sit stand test. Health-oriented applications are poorly developed, limited to a few publicly available image management and annotation tools. While automated analysis tools do exist, they lack focus on health applications. For example, existing software tools emphasize counting and tracking customers, monitoring transportation behavior, and security concerns in the private and defense sectors. Cancer prevention and control could be improved with new tools for automated analysis, primary prevention such as improved evaluation of interventions to encourage physical activity, to enhanced epidemiological studies, to automation in monitoring of symptoms and response to treatment for disease affecting physical performance, to improved compliance with cancer treatments or physical rehabilitation regimens.

SIFT Approach
SIFT and Wake Forest School of Medicine created the Characterizing Human Activities for Cancer Health Awareness (CHA-CHA) system, which recognizes activities and activity performance, and then translates that information into a human-interpretable explanation. CHA-CHA allows patients to live their lives at home and unburdened while physicians gain access to activity and performance records key to monitoring their health state between visits. CHA-CHA recognizes activity and performance from video taken on a smart phone, sending reports and alerts directly to their physician. We used state-of-the-art AI techniques that combine Neural Networks and Symbolic Reasoning to gather and reason over symbolic information to recognize activities patients perform in video. Our SME at Wake Forest School of Medicine ensured activities and performance parameters are directly relevant to the cancer health domain and evaluated the information provided to physicians via a series of usability tests. Preliminary results show the classification accuracy of our system is comparable to state-of-the-art black box systems, yet the CHA-CHA system goes beyond them by providing human-readable explanations for both classification and performance deviation detection.

Project Short Title (acronym):

CHA-CHA

Date Initiated:

Wednesday, September 1, 2021

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Project Full Title Hidden:

CHA-CHA: Characterizing Human Activities for Cancer Health Awareness

Project Shortest Title Hidden:

CHA-CHA

Prevent Workflow Messages:

Primary Contacts:

Richard

Solving POMDPs online through HTN Planning and Monte Carlo Tree Search

rpgoldman — Tue, 09 Nov 2021 20:50:30 +0000

This paper describes our ShoppingSpree HTN algorithm for online planning in Partially Observable Markov Decision Processes (POMDPs). ShoppingSpree combines the HTN planning algorithm from SHOP3, extensions to SHOP3's representation to handle partial observability, and Monte Carlo Tree Search for efficient sampling in the problem space. This paper presents only the algorithm and initial notes on the implementation: this is work in progress.

Citation:

Goldman, Robert P., "Solving POMDPs online through HTN Planning and Monte Carlo Tree Search," Fourth ICAPS Workshop on Hierarchical Planning (HPlan), 6 August 2021.

Date Published:

Monday, August 9, 2021

Publication File:

goldman2021mctshtn.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Extending Biology Models with Deep NLP over Scientific Articles

apaullada — Thu, 10 Dec 2015 18:33:02 +0000

This paper describes R3 (Reading, Reasoning, and Reporting), our system for deep language understanding and model management for the biomedical domain. Starting from a base BioPAX model, we learn extensions to it by reading biomedical research articles from PubMed Central. We describe the particular issues for text understanding in this domain and how we use pre- and post-analysis reasoning to bridge the differences in how knowledge is packaged in a text versus a biomedical database. We close with brief description of our first year results, where R3 was faster than all other reported systems, reading 1,000 articles in 15 minutes.

Citation:

David McDonald, Scott Friedman, Amandalynne Paullada, Rusty Bobrow, and Mark Burstein. Extending Biology Models with Deep NLP over Scientific Articles. In AAAI-16 Workshop on Knowledge Extraction from Text, Forthcoming.

Date Published:

Saturday, February 13, 2016

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

FUZZBUSTER: Towards Adaptive Immunity from Cyber Threats

admin — Fri, 20 Nov 2015 22:31:46 +0000

Today’s computer systems are under relentless at- tack from cyber attackers armed with sophisticated vulnerabil- ity search and exploit development toolkits. To protect against such threats, we are developing FUZZBUSTER , an automated system that provides adaptive immunity against a wide variety of cyber threats. FUZZBUSTER reacts to observed attacks and proactively searches for never-before-seen vulnerabilities. FUZZBUSTER uses a suite of fuzz testing and vulnerability assessment tools to find or verify the existence of vulnerabilities. Then FUZZBUSTER conducts additional tests to characterize the extent of the vulnerability, identifying ways it can be triggered. After characterizing a vulnerability, FUZZBUSTER synthesizes and applies an adaptation to prevent future exploits.

Citation:

David J. Musliner, Jeffrey M. Rye, Dan Thomsen, David D. McDonald, Mark H. Burstein, and Paul Robertson, "FUZZBUSTER: Towards Adaptive Immunity from Cyber Threats", SASO-11 Awareness Workshop, October, 2011.

Date Published:

Saturday, October 1, 2011

Publication File:

saso11.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Embedding planning technology into satellite systems

admin — Fri, 20 Nov 2015 22:22:39 +0000

Citation:

David Kortenkamp, Pete Bonasso, David J. Musliner, Michael J. S. Pelican, and Jesse Hostetler, Embedding Planning Technology into Satellite Systems, AIAA Infotech@Aerospace 2011 Conference, 2011.

Date Published:

Thursday, September 1, 2011

Publication File:

aero11.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Automatically Repairing Stripped Executables with CFG Microsurgery

sfriedman — Thu, 10 Sep 2015 19:12:35 +0000

BINSURGEON is a binary rewriting system that enhances stripped binary executables with repairs, defenses, and additional functionality. This involves making space-consuming changes to the program’s control flow graph (CFG), recomputing instruction content, and relocating instructions, all while preserving functionality in the remainder of the program’s control flow. BINSURGEON uses extendable rewrite templates that enable other systems to specify and parameterize program modifications, which allows BINSURGEON to be a fully-automatic component of a larger system. In this paper, we describe BINSURGEON in the context of the FUZZBOMB automated program analysis and repair system. We outline BINSURGEON’s general binary rewriting algorithm for modifying CFGs according to FUZZBOMB’s rewrite templates. We also review some of FUZZBOMB’s rewrite templates to demonstrate the diverse repair and defense strategies— including stack protection, heap protection, CFI, pointer-checking, and more— that are implemented by BINSURGEON to harden and repair vulnerable binaries.

Citation:

Scott E. Friedman, David J. Musliner. (2015). Automatically Repairing Stripped Executables with CFG Microsurgery. Fourth annual SASO workshop on Adaptive Host and Network Security. Boston, MA.

Date Published:

Thursday, September 10, 2015

Publication File:

main.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Self-Adaptation Metrics for Active Cybersecurity

sfriedman — Thu, 10 Sep 2015 19:05:11 +0000

FUZZBUSTER is a host-based adaptive security system that automatically discovers, refines, and repairs vulnerabilities in hosted applications in order to prevent cyberattacks. FUZZBUSTER must decide when to adapt its applications, when to revoke its previous adaptations, and when to sacrifice functionality to improve security. This requires an adaptation quality metric that captures (1) an application’s susceptibility to cyberattacks and (2) an application’s functionality, since adapting an application affects both of these factors. FUZZBUSTER uses different types of test cases to measure security and functionality. In this paper, we describe FUZZBUSTER’s adaptation metrics and we present two different policies for balancing security and functionality. We provide empirical results comparing these policies, and we also demonstrate how FUZZBUSTER can temporarily sacrifice the functionality of hosted applications to increase host security, and then restore functionality when more favorable adaptations are found.

Citation:

David J. Musliner, Scott E. Friedman, Tom Marble, Jeffrey M. Rye, Michael W. Boldt, Michael Pelican. (2013). Self-Adaptation Metrics for Active Cybersecurity. Second annual SASO workshop on Adaptive Host and Network Security. Philadelphia, PA.

Date Published:

Thursday, September 5, 2013

Publication File:

ahans13.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Meta-control for Adaptative Cybersecurity in FUZZBUSTER

sfriedman — Thu, 10 Sep 2015 18:54:08 +0000

Modern cyber attackers use sophisticated, highly-automated vulnerability search and exploit development tools to find new ways to break into target computers. To protect against such threats, we are developing FUZZBUSTER, a host-based adaptive security system that automatically discovers faults in hosted applications and incrementally refines and repairs the underlying vulnerabilities. To perform this self-adaptation, FUZZBUSTER uses meta-control to coordinate a diverse and growing set of custom and off-the-shelf fuzz-testing tools. FUZZBUSTER's greedy meta-control strategy considers adaptation deadlines, the exploit potential of vulnerabilities, the usage schedule of vulnerable applications, and the expected performance of its various fuzz-testing and adaptation tools. In this paper, we demonstrate how FUZZBUSTER's meta-control reasons efficiently about these factors, managing task selection to maximize the system's safety and effectiveness.

Citation:

David J. Musliner, Scott E. Friedman, Jeffrey M. Rye, Tom Marble. (2013). Meta-control for Adaptative Cybersecurity in FUZZBUSTER. Proceedings of SASO 2013. Philadelphia, PA.

Date Published:

Thursday, September 12, 2013

Publication File:

saso13.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Automated Fault Analysis and Filter Generation for Adaptive Cybersecurity

sfriedman — Thu, 10 Sep 2015 18:51:18 +0000

We are developing the FUZZBUSTER system to automatically identify software vulnerabilities and create adaptations that shield or repair those vulnerabilities before attackers can exploit them. Adaptive cybersecurity involves efficiently improv- ing software security to minimize the window of attack, and also preserving software functionality as much as possible. This paper presents new tools that have been integrated into FUZZBUSTER adaptive cybersecurity. These tools produce more general, accurate adaptations, increase the efficiency of FUZZBUSTER’s diagnoses and adaptation operations, and preserve the software’s functionality. We report the results of FUZZBUSTER’s analysis of 16 fault-injected command-line binaries and six previously known bugs in the Apache web server. We compare results over different configurations of FUZZBUSTER to characterize the benefits of the new fuzz-testing tools.

Citation:

David J. Musliner, Scott E. Friedman, Jeffrey M. Rye. (2014). Automated Fault Analysis and Filter Generation for Adaptive Cybersecurity. ADAPTIVE 2014 : The Sixth International Conference on Adaptive and Self-Adaptive Systems and Applications. Venice, Italy. Best Paper Award.

Date Published:

Wednesday, March 5, 2014

Publication File:

adaptive14.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Improving Automated Cybersecurity by Generalizing Faults and Quantifying Patch Performance

sfriedman — Thu, 10 Sep 2015 18:48:49 +0000

We are developing the FUZZBUSTER system to automatically identify software vulnerabilities and create adaptations that shield or repair those vulnerabilities before attackers can exploit them. FUZZBUSTER’s goal is to minimize the time that vulnerabilities exist, while also preserving software functionality as much as possible. This paper presents new adaptive cybersecurity tools that we have integrated into FUZZBUSTER, as well as new metrics that FUZZBUSTER uses to assess their performance. FUZZBUSTER’s new tools increase the efficiency of its diagnosis and adaptation operations, they produce more general, accurate adaptations, and they effectively preserve software functionality. We present FUZZBUSTER’s analysis of 16 fault-injected command-line binaries and six previously known bugs in the Apache web server. We compare FUZZBUSTER’s results for different adaptation strategies and tool settings, to characterize their benefits.

Citation:

Scott E. Friedman, David J. Musliner, Jeffrey M. Rye. (2014). Improving Automated Cybersecurity by Generalizing Faults and Quantifying Patch Performance. International Journal on Advances in Security, 7(3&4). pp. 121-130.

Date Published:

Monday, December 1, 2014

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages: