Using Identity Credential Usage Logs to Detect Anomalous ...

Using Identity Credential Usage Logs to Detect Anomalous ...

Using Identity Credential Usage Logs to Detect Anomalous Service Accesses ACM DIM 2009, Chicago, IL, 2009 Daisuke Mashima Dr. Mustaque Ahamad College of Computing Georgia Institute of Technology Atlanta, GA, USA Increasing Risk of Identity Theft Variety of online identity credentials Passwords, certificates, SSN, credit card number, etc.

Loss and theft are possible and common Consequence of online identity theft Impersonation Disclosure of sensitive information Financial loss 2 To counter such threats Online service providers are required to Analyze huge amount of log records to identify suspicious service accesses Investigate identified records extensively

In reality Significant reliance on human experts Not processed in real-time basis Automated mechanism to monitor identity usage (service accesses) is desired. 3 Outline

Observations from real data sets Our approach Anomaly-based risk scoring scheme Preliminary evaluation Conclusion / Future Work 4 Buzzport Access Log 5 Buzzport Access Log

380484533347391, 380484533347391, 380484533347391, 380484533347391, 380484533347391, 24/08/2007 14:07:05, 27/08/2007 08:01:14, 27/08/2007 08:04:36, 27/08/2007 12:05:36, 31/08/2007 14:31:43, 24/08/2007 14:18:46 27/08/2007 08:02:54

27/08/2007 08:16:05 27/08/2007 12:18:15 31/08/2007 14:38:08 Contain only (Anonymized) User ID Login timestamp Logout timestamp 6 Another data set Log records of a portal of online trading company

The following items are available: User ID Coarse Action Type (Login / Logout) Timestamp IP Address Organization Name etc. 7 Observations and Considerations Available information is quite limited. Typical fraud detection systems rely on much richer information Data are not labeled.

Supervised techniques are not available. Limited types of events can be observed. Schemes relying on event sequence or state transition have limited applicability. 8 Our Approach Utilize attributes derived from an individual identity usage record Timestamp (day-ofweek etc.), IP address, etc. Focus on categorical attributes Build user profile based on occurrence

frequency of each attribute value Determine risk scores based on frequency information 9 User Profile Management Defined as a frequency distribution of attribute values (categories) One profile for one attribute Multiple profiles can be defined per user. Day-of-week profile, hour-of-day profile, and so forth Updated upon receipt of each log record Simply increment occurrence counters corresponding

to the attribute values in the record Data aging can be easily implemented Periodically multiply all counters with some decay factor 10 Base Score and Weight Base score represents how unlikely an observed users access is. BaseScore = -log (RelativeFrequency) Score weight quantifies the effectiveness of each attribute for profiling.

When an attribute well characterizes users identity usage pattern, the value should be high. How can we quantify it? 11 Score Weight Use distance between the frequency distribution and uniform distribution as weight Bhattacharyya Distance etc. Data aging is necessary. 0.25 0.2 0.15

0.1 23 21 17 15 19 Hour of Day

13 11 9 7 5 0 3

0.05 1 Relative Frequency 12 Score Aggregation Sub Score (a product of a base score and the corresponding weight) are computed. Sub Score is computed for each profile. How can we combine Sub Scores?

Pick the MAX of Sub Scores Weighted sum of Sub Scores Others? 13

Setting of Experiments Buzzport data set Profiling attributes Week of month (5 categories) Day of week (7 categories) Hour of Day (24 categories) Scale Sub Scores in [0, 100) Use MAX of 3 Sub Scores as output 14 Trends of Risk Scores 15

Trends of Risk Scores with Data Aging Decay Factor = 0.5 is applied monthly. 16 False Positive / True Positive Analysis Randomly pick 5 users with different access frequency Split each users log records into two: Test data: last 1 month Training data: Rest of them

Analyze False Positive rate by using the same users training data and test data Analyze True Positive rate by using different users data sets (a.k.a Cross Profiling) 17 False Positive / True Positive Results * Each users threshold is determined based on the score range of the training data. 18 Time / Storage Cost Measured on Linux PC with Intel Core 2 Duo E6600 and 3GM RAM

Average time per record: 5ms Good enough for real-time processing Storage space per user: 1.4KB Potential to accommodate a large number of users 19 Conclusion Defined design principles for risk scoring based on identity usage logs Proposed a way to compute anomalybased risk scores in real-time basis Presented a prototype system using time

stamp information and showed that it has reasonably good accuracy 20 Future Work Investigate other attributes (E.g. location) Conduct detailed experiments Evaluate with other data sets Find the optimum configuration Integrate into other security mechanisms 21

Thank you very much. Questions? [email protected] 22

Recently Viewed Presentations

  • Wave properties Wave behaviour We now look to

    Wave properties Wave behaviour We now look to

    The end of the rope if fixed - reflected pulse returns inverted. Imagine whip. Some of the energy of the pulse will actually be absorbed at the support and as such, the amplitude of the reflected pulse will be less...
  • Proteomic Analysis for Biomarkers in Early Detection of Cancer

    Proteomic Analysis for Biomarkers in Early Detection of Cancer

    Proteomic Analysis for Biomarkers in Early Detection of Cancer Sherry Funston Emily Faerber Brandon Lesniak Protein Biomarkers Proteins used as an indicator of a specific state (such as a disease) Changes in protein expression or state can be "biomarkers" for...
  • Economics Quiz of the week w/e 11/11/2016 Press

    Economics Quiz of the week w/e 11/11/2016 Press

    Chinese e-commerce giant Alibaba had its annual 'Singles Sales' day this week, with record sales recorded. How much turnover did they make in just one day?
  • Records C++ Structs

    Records C++ Structs

    A function can return a value of the type struct Note example program fragment Contrast Arrays and structs Arrays of Records First declare a struct (such as part_struct) Then specify an array of that type Access elements of the array,...
  • Sub  1 Ohm Broadband Impedance Matching Network Design

    Sub 1 Ohm Broadband Impedance Matching Network Design

    ZMeas ZCal e.g. for a ZCal point, what is the Output Tuner's Load reflection coefficient when ZMeas is normalized to the ZCal point 50 Ω ZMeas (calibrated impedance vs. actual impedance during measurement) * * * * * * *...
  • Chinese Baptist Church of San Jose

    Chinese Baptist Church of San Jose

    Victory Chant (4) Joseph Vogels 1985 Scripture in Song CCLI 522161 Victory Chant Hail Jesus You're my King Hail Jesus You're my king Your life frees me to sing. Your life frees me to sing. I will praise You all...
  • "I am a Canadian, free to speak without fear, free to worship ...

    "I am a Canadian, free to speak without fear, free to worship ...

    The Diefenbaker family moved west in 1903, for his father to accept a position near Fort Carlton, then in the Northwest Territories (now in Saskatchewan). John Diefenbaker had been interested in politics from an early age, and told his mother...
  • Dr. n. med. Daniel Zielonka Koordynator EHDN Polska

    Dr. n. med. Daniel Zielonka Koordynator EHDN Polska

    Uczestnicy badania są rekrutowani z: Ameryki Północnej, Ameryki Środkowej, Europy, Azji, Australii i Nowej Zelandii. ... Celem organizacji jest nie tylko odkrycie lekarstwa na HD ale także poprawa jakości życia pacjentów z HD poprzez umożliwienie wykorzystania i usprawnianie obecnie ...