1. Statistical Disclosure Control Mark Elliot Confidentiality and Privacy Group CCSR University of Manchester

2. Overview CAPRI –who we are / what we do SDC – some basics SD Risk Assessment and Microdata –General Concepts –Our Approach SD Risk Assessment and Aggregate Data –General Concepts –Our Approach Statistical Disclosure and the Grid

3. C onfidentiality A nd PRI vacy group www.ccsr.ac.uk/capri University of Manchester

4. Purpose To investigate the Confidentiality and Privacy issues that arise from the collection, dissemination and analysis of data.

5. Multidisciplinary Approach Mark Elliot, Knowledge and Data Engineering Kingsley Purdam, Politics and Information Society Anna Manning, Data Mining and HPC Elaine Mackey, Social Policy Duncan Smith, Statistics and Stochastic Systems Karen McCullagh, the Law and Social Policy

6. Associate Members in Manchester C S: Alan Rector, John Gurd, Len Freeman, Adel Taweel. Computation: John Keane. Psychology: Karen Lander, Lee Wickham. Medicine: Iain Buchan. Manchester Computing Centre: Stephen Pickles. Law:Joseph Jakaneli, John Harris.

7. Research Programmes The Social and Political Aspects of Confidentiality and Privacy The Detection of Risky Records: Special Uniqueness The Disclosure risk issues posed by the Grid High Performance Computing and statistical Disclosure Medical Records: Clinical E-Science Framework The SAMDIT methodology: Data Monitoring Centre

8. Consultancy ONS Census Social Survey Neighbourhood statistics US Census Bureau Australian Bureau of Statistics Statistics New Zealand

9. Statistical Disclosure Control

10. Sub Fields Disclosure risk assessment. Disclosure control methodology. Analytical validity. Microdata and Aggregate data. Business and Personal data. Intentional and Consequential data

11. Our General Approach: The SAMDIT method Scenario Analysis (Elliot and Dale 1999) Metric Development Implementation Testing

12. Microdata

13. The Microdata Disclosure Risk Problem:An Example NameAddressSexAge.. Income.. SexAge.. ID variables Key variables Target variables Identification file Target file

14. Risk Assessment methods File Level –Population Uniqueness e.g Bethlehem(1990), Samuels(1998) –DIS; Skinner and Elliot(2002) Record level –Statistical modelling (Fienberg and Makov 1998, Skinner and Holmes 1998) –Computational Search Elliot et al (2002)

15. Data Intrusion Simulation Uses microdata set (or table) itself to estimate risk - no population data. An estimate of the probability of a correct match (given a unique match). Special method: sub-sampling and re- sampling. General method: derivation from the equivalence class structure.

16. The DIS Method Remove a small number of records Microdata sample

17. The DIS Method II Copy back a random number of the removed records (at a probability equivalent to the original sampling fraction)

18. The DIS Method III Match the removed fragment against the truncated microdata file

19. Validation Empirical validation studies comparing with the results obtained using population data: Empirical results: No bias and small error. Elliot (2001) Mathematical proof: Skinner and Elliot (2002).

20. Pr(cm|um) for 2% sample with basic key (age sex marital status)

21. Levels of Risk Analysis DIS –Works at the file level –Very good for comparative analyses e.g. SAMs

22. Levels of Risk Analysis Record level risk is important –Variations in risk topography –Risky records

23. Special Uniques Original concept –Counterintuitive geographical effect, indicated two types of sample uniques. –Random and Special –Special Epidemiological peculiarity –Random Effect of sampling and variable definition

24. Special Uniques Changing definition: 1.Sample uniques which remain unique despite geographical aggregation 2.Sample uniques which remain unique through any variable aggregation 3.Sample uniques on subset of key variables 4.Dichotomy to Dimension

25. Minimal Sample Unique A set of sample unique set of variable values –for which no subset is also unique.

26. Risk Signatures: combinations of minimal uniques Example –Unique pairs 0 –Unique triples 5 –Unique fourfolds 1 –Unique fivefolds 3 –Unique sixfolds 0 –Unique sevenfolds 0 –………

27. Special Uniques Problem: how to look at all the variables? –File may contain hundreds –Even with scenario keys individual records can contain hundreds of minimal sample uniques –Combinatorial explosion

28. HIPERSTAD Projects Funded by ESRC, ONS and EPSRC Use of high performance computing –Enables comprehensive analysis of patterns of uniqueness within each record –Has allowed investigation of more complex grading systems

29. Risk Signatures II Allow grading and classification of records –Differential treatment –Low impact high efficacy disclosure control

30. Combining DIS and SUDA A heuristic method for combining the two methods to provide a per record matching confidence has proved very effective ONS evaluation studies show that combined method picks out high probability risk very well

31. SUDA software Available free under licence Used at ONS, ABS and Stats new Zealand

32. Aggregate Data

33. Introduction Measurement of Disclosure Risk is an important precursor for its control Intruder/scenario based metrics are better than abstract ones Such metrics are available for microdata but not for aggregate data

34. Overview Overview of the issues and introducing the method on a conceptual level Details of the algorithms Ongoing and Future Work

35. The Issues Aggregate data is usually 100% data, so measures based on identification disclosure and sampling are meaningless A better approach is to evaluate what can be inferred through attribute disclosure

36. Attribute Disclosure

38. The Approach Rather than assess the risk of actual attribute disclosure we propose estimating the probability of producing a potentially disclosive table, which we define as any table containing at least one zero The method/measure we propose can be applied to: –Single tables –Groups of tables –Unperturbed and perturbed tables –Unpublished tables

39. The Bounds Problem In a general sense any set of tables can be viewed as a set of bounds on the full table. For example if we release two one way frequency tables:

40. The Bounds Problem We are effectively releasing the marginals to a two-way frequency table where the entire joint distribution has been suppressed

41. The cells in the joint distribution can be expressed as a set of bounds (or ranges of feasible values)

42. The Subtraction – Attribution Probability (SAP) Method The risk associated with a table release depends on the set of tables jointly, rather than on the individual tables. SAP can be used on single tables, groups of tables, perturbed or unperturbed tables. Bounds are calculated and then the probability of an intruder producing one or more upper bounds of zero by subtracting k random individuals from the table is calculated The output can be set for user defined levels of k

43. Var1 Var2AB C39 D22 Var1 Var3AB E110 F41

44. Var2 Var3CD E83 F41 Var1 and Var2 Var3A, CA, DB, CB, D E0182 F3110 Original cell counts can be recovered from the marginal tables

45. Subtraction We consider that an intruder might have knowledge of the relevant population, as well as information in the table release We assume (at least initially) that the intruder has perfect knowledge of k randomly selected individuals

46. Single exact tables The lower / upper bounds are equal to the published counts The probability of an intruder recovering at least one zero by subtracting known individuals is found by calculating Hypergeometric probabilities and applying the inclusion / exclusion principle

47. The marginal probability of observing all individuals in a cell is calculated for each individual cell, and the sum is added to a total (initially zero) The marginal probability of observing all individuals in a pair of cells is calculated for each pair of cells, and subtracted from the total The marginal probability of observing all individuals in a triple of cells is calculated for each triple of cells, and added to the total And so on, until we have considered the table total, or all subsequent probabilities are zero

48. For example, For k = 3 and the following table (and not showing zero probability terms), 124

49. Example output

50. 1)What new data possibilities does the Grid provide and what confidentiality implications do they have? 2)How could the Grid (or a Grid) be used to enable disclosure risk assessment and control? 3)How could a grid enable a data intruder? 4)What are the possibilities and issues provided by remote access? Confidentiality and the Grid

51. New data One of the key potentials for the Grid is the possibility of bringing together different data sources through linking and fusing. This is precisely the disclosure risk situation. Our pilot project work shows that adding a third data set tends to increases the linkability of two other datasets.

52. New Access Virtual remote access has the potential to provide a safe setting model for data access. New question how safe is that output?

53. Data Intrusion Detection Virtual access allows the possibility of monitoring use. Use patterns by user and across users can be analysed for patterns resembling intrusion (similar to fraud detection).

54. Confidential data access via a grid PRE-ACCESS Data Quality Monitor Raw Datasets Treated Datasets Data Intrusion sentry Grid Firewall PRE-OUTPUT Disclosure Control PRE-ACCESS Disclosure Control PRE-Output Data Quality Monitor User Analytical request

55. Conclusions Statistical Disclosure Control is a maturing field. –Basic issues well defined –Theory and Practice still in development Grid presents new opportunities and new confidentiality risks.

56. Finally a plug….. International Symposium on Confidentiality, Privacy and Disclosure in the 21 st Century –Date: 3 rd May –Venue: Manchester MANDEC Centre –See www.ccsr.ac.uk/capri/symposiumwww.ccsr.ac.uk/capri/symposium