Download Inference Control in Statistical Databases: From Theory to by Josep Domingo-Ferrer (auth.), Josep Domingo-Ferrer (eds.) PDF

By Josep Domingo-Ferrer (auth.), Josep Domingo-Ferrer (eds.)

Inference regulate in statistical databases, sometimes called statistical disclosure hindrance or statistical confidentiality, is set discovering tradeoffs to the stress among the expanding societal want for exact statistical info and the felony and moral legal responsibility to guard privateness of people and businesses that are the resource of information for generating information. suggestions utilized by intruders to make inferences compromising privateness more and more draw on information mining, list linkage, wisdom discovery, and knowledge research and hence statistical inference keep watch over turns into an essential component of machine science.
This coherent cutting-edge survey offers probably the most fresh paintings within the box. The papers provided including an creation are prepared in topical sections on tabular facts security, microdata safeguard, and software program and person case studies.

Show description

Read Online or Download Inference Control in Statistical Databases: From Theory to Practice PDF

Similar computers books

The Ni-YSZ interface

The anode/electrolyte interface ш reliable oxide gas cells (SOFC) is understood to reason electric losses. Geometrically basic Ni yttria-stabilised zirconia (YSZ) interfaces have been tested to realize info at the structural and chemical alterations taking place in the course of experiments at 1000°C in an environment of ninety seven% H2/3% H20.

Handbook of Computer Vision and Applications, V1

The instruction manual of machine imaginative and prescient and functions, Three-Volume Set is on one of many "hottest" topics in modern day intersection of utilized Physics, computing device technology, electric Engineering, and utilized arithmetic. the individuality of this set is that it's very applications-oriented. Examples of functions in numerous fields of recent technology are really emphasised.

Additional resources for Inference Control in Statistical Databases: From Theory to Practice

Sample text

Geurts [7] refined this model, and reported computational experiences on small-size instances, the largest instance solved to optimality being a table with 20 rows, 6 columns and 17 sensitive cells. (the computing time is not reported; for smaller instances, the code required several thousand CPU seconds on a SUN Spark 1+ workstation). Gusfield [8] gave a polynomial algorithm for a special case of the problem. Heuristics for 3-dimensional tables have been proposed in Robertson [14], Sande [16], and Dellaert and Luijten [4].

Figure 3 shows a first attempt to have an integer linear model. Clearly, this new model is a Mixed Integer Linear Programming model, and therefore —in theory— there are efficient approaches to solve it. Nevertheless, the number of new variables (fikp and gikp ) is really huge even on small tables. For example, the model associated with a table with 100 × 100 cells with 1% 42 Juan Jos´e Salazar Gonz´ alez wi xi min i∈I subject to: i∈I mij fikp = bj ai − (ai − lbki )xi ≤ fikp ≤ ai + (ubki − ai )xi i∈I mij gikp = bj ai − (ai − lbki )xi ≤ gikp ≤ ai + (ubki − ai )xi for all j ∈ J for all i ∈ I for all j ∈ J for all i ∈ I fpkp ≥ ap + upl kp gpkp ≤ ap − lpl kp fpkp − gpkp ≥ spl kp for all p ∈ P and all k ∈ K, and also subject to: xi ∈ {0, 1} for all i ∈ I.

Examples 7b,c of [4] are 3-DIPTP exhibiting one or more non-integer continuous exact bounds. Because it is based on iterative improvement of integer upper bounds, in these situations the shuttle algorithm can come no closer than one unit larger than the exact integer bound, and therefore is incapable of achieving the exact integer bound. The shuttle algorithm is not new: it was introduced by Schell [1] towards purported sufficient conditions on the 2-dimensional marginals for feasibility of 3-DPTP.

Download PDF sample

Rated 4.88 of 5 – based on 32 votes