Validating EMR Audit Automation Carl A. Gunter University of Illinois Accountable Systems Workshop.

Slides:



Advertisements
Similar presentations
Developing e-health solutions to improve patient safety in primary care Report on an NPSA-funded project Professor Tony Avery University of Nottingham.
Advertisements

Information Visualization for an Intrusion Detection System Ching-Lung Fu James Blustein Daniel Silver.
LADIS workshop (Oct 11, 2009) A Case for the Accountable Cloud Andreas Haeberlen MPI-SWS.
Joint Sentiment/Topic Model for Sentiment Analysis Chenghua Lin & Yulan He CIKM09.
5/1/2006Sireesha/IDS1 Intrusion Detection Systems (A preliminary study) Sireesha Dasaraju CS526 - Advanced Internet Systems UCCS.
This work is supported by the National Science Foundation under Grant Number DUE Any opinions, findings and conclusions or recommendations expressed.
Flash Crowds And Denial of Service Attacks: Characterization and Implications for CDNs and Web Sites Aaron Beach Cs395 network security.
Intrusion detection Anomaly detection models: compare a user’s normal behavior statistically to parameters of the current session, in order to find significant.
seminar on Intrusion detection system
Scaling and Attitude Measurement in Travel and Hospitality Research Research Methodologies CHAPTER 11.
Stephen S. Yau CSE , Fall Security Strategies.
Lecture 11 Intrusion Detection (cont)
Department Of Computer Engineering
Mastering Windows Network Forensics and Investigation Chapter 14: Other Audit Events.
CBR in Medicine Jen Bayzick CSE435 – Intelligent Decision Support Systems.
Anomaly detection Problem motivation Machine Learning.
Data Mining for Intrusion Detection: A Critical Review Klaus Julisch From: Applications of data Mining in Computer Security (Eds. D. Barabara and S. Jajodia)
Chapter 22 Systems Design, Implementation, and Operation Copyright © 2012 Pearson Education, Inc. publishing as Prentice Hall 22-1.
CS490D: Introduction to Data Mining Prof. Chris Clifton April 14, 2004 Fraud and Misuse Detection.
Modeling and Detecting Anomalous Topic Access Siddharth Gupta 1, Casey Hanson 2, Carl A Gunter 3, Mario Frank 4, David Liebovitz 4, Bradley Malin 6 1,2,3,4.
Intrusion Detection for Grid and Cloud Computing Author Kleber Vieira, Alexandre Schulter, Carlos Becker Westphall, and Carla Merkle Westphall Federal.
JCAHO UPDATE June The Bureau of Primary Health Care is continuing to encourage Community Health Centers to be JCAHO accredited. JCAHO’s new focus.
Intrusion Detection Adam Ashenfelter Nicholas J. Tyrrell.
Improving Intrusion Detection System Taminee Shinasharkey CS689 11/2/00.
Risk Management - the process of identifying and controlling hazards to protect the force.  It’s five steps represent a logical thought process from.
Thesis Proposal PrActive Learning: Practical Active Learning, Generalizing Active Learning for Real-World Deployments.
ACM BCB 2015 Xun Lu 1*, Aston Zhang 1*, Carl A. Gunter 1, Daniel Fabbri 2, David Liebovitz 3, Bradley Malin 2 1 University of Illinois at Urbana-Champaign,
nd Joint Workshop between Security Research Labs in JAPAN and KOREA Profile-based Web Application Security System Kyungtae Kim High Performance.
Uncovering Anomalous Usage of Medical Records via Social Network Analysis You Chen, Ph.D. Biomedical Informatics Dept., School of Medicine EECS Dept.,
Using Identity Credential Usage Logs to Detect Anomalous Service Accesses Daisuke Mashima Dr. Mustaque Ahamad College of Computing Georgia Institute of.
Intrusion Detection Prepared by: Mohammed Hussein Supervised by: Dr. Lo’ai Tawalbeh NYIT- winter 2007.
Clinical Decision Support Nasriah Zakaria, Ph.D. Assistant Professor Medical informatics and e-learning unit (MIELU) College of Medicine, King Saud university.
Making a Claim Grounds for Claim Evaluation Beyond Brainstorm.
Evaluation of routine data sources for ascertainment of hypospadias cases Congenital Anomaly Register for Oxfordshire, Berkshire, and Buckinghamshire (CAROBB)
Transfer Learning Task. Problem Identification Dataset : A Year: 2000 Features: 48 Training Model ‘M’ Testing 98.6% Training Model ‘M’ Testing 97% Dataset.
Kittiphan Techakittiroj (25/10/58 12:06 น. 25/10/58 12:06 น. 25/10/58 12:06 น.) Intrusion Detection System Kittiphan Techakittiroj
Preparing for the worst,
Principles of Information Systems, Sixth Edition Specialized Business Information Systems Chapter 11.
Urban Infrastructure and Its Protection Responding to the Unexpected Interest Group Report Group Members G. Giuliano (USC), Jose Holguin-Veras (CUNY),
Lecture 16 Section 8.1 Objectives: Testing Statistical Hypotheses − Stating hypotheses statements − Type I and II errors − Conducting a hypothesis test.
SECURITY AND DATA NORMALIZATION COLLABORATION sharps.org Discussion by Mark Frisse and Carl Gunter.
Network Perimeter Defense Josef Pojsl, Martin Macháček, Trusted Network Solutions, Inc.
1 Chapter 9 Intruders. 2 Outline Intruders –Intrusion Techniques –Password Protection –Password Selection Strategies –Intrusion Detection Statistical.
Record Authenticity as a Measure of Trust: A View Across Records Professions, Sectors, and Legal Systems Corinne Rogers University of British Columbia.
Drug & Poison Control center
Understand Audit Policies LESSON Security Fundamentals.
CS526: Information Security Chris Clifton November 25, 2003 Intrusion Detection.
High Assurance Products in IT Security Rayford B. Vaughn, Mississippi State University Presented by: Nithin Premachandran.
Intrusion and intrusion detection Published online 27 July 2001 by John McHugh, © Springer-Verlag 2001 Presented by Po-yuan Peng.
IS3220 Information Technology Infrastructure Security
Medical Hypothesis Testing July 27, 2006 Bill Bushey Emily Jenkins.
HIPS. Host-Based Intrusion Prevention Systems  One of the major benefits to HIPS technology is the ability to identify and stop known and unknown attacks,
Under the Shadow of Sunshine: Understanding and Detecting Bulletproof Hosting on Legitimate Service Provider Networks Sumayah Alrwais, Xiaojing Liao, Xianghang.
Application Intrusion Detection
Auditing Concepts.
Design of Expert Systems
Intrusion Control.
Clinical Study Results Publication
Evaluating a Real-time Anomaly-based IDS
9. Introduction to signal detection
School of EE and Computer Science
Flavio Toffalini, Ivan Homoliak, Athul Harilal,
Join In Be Secure Presentation
Effects of IT on Consideration of Internal Control in a Financial Statement Audit Dr. Donald McConnell Jr. 12/1/2018.
Objectives Telecommunications and Network Physical and Personnel
CORE Security Technologies
Intrusion Detection Systems
Introduction to public health surveillance
IoT in Healthcare: Life or Death
Presentation transcript:

Validating EMR Audit Automation Carl A. Gunter University of Illinois Accountable Systems Workshop

Situation Access to hospital Electronic Medical Record (EMR) data suffers risk of high loss in the event of false negatives (incorrect refusal of access). – Example: doctor acting on an emergency cannot get access to list of allergies. Hospital has highly trained personnel in whom much trust is vested. Consequences Hospital access systems give liberal access to records, relying on accountability. Insider threats are serious and abuses are widely documented. Accesses are too numerous to review manually by experts. Automated support is required. Root Problem Statement

Ideal Approach Obvious approach: develop anomaly detector (AD) with rules and train classifiers on bad and good accesses. Run the AD on the audit logs and investigate positives manually with domain experts Problem This requires considerable dependence on experts. Assumes experts know how to provide labels. Assumes experts can formulate rules. Assumes labeled training sets exist and that researchers will be able to get access to them. Validation Problem Statement

The primary validation approach applied by researchers in this area can be called the Random Object Access Model (ROAM). ROAM is based on the premise that anomalous users and accesses look random. Strategy – Develop rules and train classifier on real data set augmented with synthetic random users and accesses. – Test ability to recognize random users or accesses. Primary Validation Approach

Pro Likely that illegitimate accesses appear random. Good ROAM classifier prepares for expert review to identify false positives. ROAM classifier may find legitimate but interesting hospital information flows. Provides a ready testing strategy reminiscent of “fuzzing”. Con There no current quantified evidence that random accesses and illegitimate accesses have strong overlap. Indeed, there is evidence that in some cases legitimate accesses look random. Some illegitimate accesses may be systematic in ways that defy detection by ROAM classifiers. ROAM Assessment

What are the prospects for alternative models? Example: introduce specific attacks experienced “in the wild” similar to network traces enriched with known attacks. Another idea: look at problems like masquerading and open terminals. Behaviors are not random, but may display learnable characteristics. Beyond ROAMing

Explored an alternative validation model based on topic classification. Idea: Patients are “documents” and diagnoses, drugs, etc. are their “words”. Use Latent Dirichlet Allocation (LDA) to learn topics that can be used to classify patients. Use this to characterize users as readers of documents. Detect unusual readers. Detect readers of random topics. Modeling and Detecting Anomalous Topic AccessModeling and Detecting Anomalous Topic Access, Siddharth Gupta, Casey Hanson, Carl A. Gunter, Mario Frank, David Liebovitz, and Bradley Malin. IEEE Intelligence and Security Informatics, June Random Topic Access Model (RTAM)

Topic Distributions Diagnosis Topics Neoplasm TopicObstetric Topic Kidney Topic

Multidimensional Scaling: Patient Diagnosis

RTAM: Random Users a.) Direct or Masquerading User (α<1) : an anomalous user of some specialty gains sole access to the terminal of another user in the hospital. b.) Purely Random User (α=1): user is characterized by completely random behavior, with little semantic congruence to the hospital setting. c.) Indirect User: user type resembles an even blend of the topics of many specialized users.

Random Topic Access Detection (RTAD)

Results - I

Results - II

Other strategies besides ROAM may capture new types of threats. Good progress on technical measures of validation; need links to expert review and ground truth. More evaluation studies are needed. Important to integrate access audit with general business intelligence: understanding the roles and workflows of the organization. Discussion and Conclusions