Advances in Artificial Intelligent for Privacy Protection and Security 1st Edition by Agusti Solanas, Antoni Martinez Balleste ISBN 9789812790330 9812790330

Advances in Artificial Intelligent for Privacy Protection and Security 1st Edition by Agusti Solanas, Antoni Martinez Balleste – Ebook PDF Instant Download/Delivery.  9789812790330 ,9812790330 
Full download Advances in Artificial Intelligent for Privacy Protection and Security 1st Edition after payment

Product details:
ISBN 10: 9812790330 
ISBN 13: 9789812790330
Author: Agusti Solanas, Antoni Martinez Balleste

Advances in Artificial Intelligent for Privacy Protection and Security 1st Edition Table of contents:

1. Introduction A. Solanas and A. Mart¶³nez-Ballest¶e

1.1. Organization of the book

References

PART 1: A Brief Introduction to Privacy and Security

2. An Introduction to Privacy Aspects of Information and Communication Technologies A. Martinez-Ball

Contents

2.1. Introduction

2.2. Privacy and the Internet

2.2.1. Monitoring User Activity

2.2.1.1. Tracking Cookies

2.2.1.2. Spyware

2.2.1.3. Social Engineering Attacks

2.2.2. Privacy in Modern Web Services

2.2.2.1. Privacy in Social Networks

2.2.2.2. Privacy in E-Commerce

2.2.3. The Big Brothers of Internet

2.3. Privacy in Databases

2.3.1. Privacy of the Respondents

2.3.2. User Privacy

2.4. Privacy in Ubiquitous Computing

2.4.1. Location-Based Services

2.4.1.1. TTP-Based Schemes

2.4.1.2. TTP-Free Proposals

2.4.2. Radio-Frequency Identi¯cation

2.5. Conclusions

Disclaimer and Acknowledgements

References

3. An Overview of Information Security A. Ribagorda Garnacho, A. I. Gonz¶alez-Tablas Ferreres, A. A

Contents

3.1. Introduction

3.2. Vulnerabilities

3.3. Threats

3.4. Countermeasures

3.5. Authentication mechanisms

3.5.1. Something you know

3.5.2. Something you are

3.5.3. Something you have

3.6. Access control mechanisms

3.6.1. Access control policies

3.6.2. Access control models

3.6.2.1. Access matrix model

3.6.2.2. Mandatory access control models

3.7. Data encipherment mechanisms

3.7.1. Attacks

3.7.2. Cryptosystems classification

3.7.2.1. Substitution, transposition and product ciphers

3.7.2.2. Symmetric or secret key cryptosystems

3.7.2.3. Asymmetric or public key cryptosystems

3.7.3. Stream and block cryptosystems

3.8. Digital signature mechanism

3.9. Digital certificates

3.10. Audit logs

3.11. Physical security

3.11.1. Intrusion prevention

3.11.2. Electromagnetic emanations

3.11.3. Physical access control systems

References

PART 2: Privacy Protection by means of Arti¯cial Intelligence

4. Data Mining in Large Databases | Strategies for Managing the Trade-O® Between Societal Bene¯t a

Contents

4.1. Introduction

4.2. Examples of data-collecting institutions and data users

4.3. Strategies for controlling privacy

4.3.1. Input control and masked data sets

4.3.2. Output control

4.3.3. Query auditing

4.3.5. Measuring privacy and disclosure risk in published outputs

4.4. Measures of the utility of published data sets and outputs

4.5. Conclusion

References

5. Desemantization for Numerical Microdata Anonymization J. Pont-Tuset, J. Nin, P. Medrano-Gracia, J

Contents

5.1. Introduction

5.2. Background and State of the Art

5.2.1. Microdata protection scenario

5.2.2. Information loss and disclosure risk

5.2.3. State of the art in microdata anonymization methods

5.2.3.1. Rank swapping

5.2.3.2. Microaggregation

5.2.4. Artificial neural networks

5.2.4.1. The backpropagation algorithm

5.3. A New Desemantization Methodology

5.4. Data Preprocessing

5.4.1. Vectorization

5.4.2. Sorting

5.4.3. Partitioning

5.4.4. Normalization

5.4.5. Re-sorting and re-normalization

5.5. Data Fitting

5.5.1. Mean value model

5.5.2. Polynomial regression model

5.5.3. Neural networks

5.5.3.1. Normalization range

5.5.3.2. Learning process

5.5.3.3. Data protection

5.6. Experiments

5.6.1. Data sets description

5.6.1.1. The Census data set

5.6.1.2. The EIA data set

5.6.1.3. The Water-treatment data set

5.6.2. Mic1D-k evaluation

5.6.3. PoROP-k evaluation

5.6.4. ONN evaluation

5.7. Conclusions

Acknowledgments

References

6. Multi-Objective Evolutionary Optimization in Statistical Disclosure Control R. Dewri, I. Ray, I.

Contents

6.1. Introduction

6.2. Multi-objective Optimization

6.3. Statistical Disclosure Control

6.3.1. Preserving privacy

6.3.2. Estimating information loss

6.4. Evolutionary Optimization

6.4.1. Multi-objective analysis

6.4.1.1. In the absence of suppression

6.4.1.2. With pre-specified suppression tolerance

6.4.1.3. For comprehensive overview

6.4.2. Solution encoding

6.4.3. Non-dominated Sorting Genetic Algorithm-II

6.4.4. Crossover for constrained attributes

6.4.5. Population initialization

6.5. Some Empirical Results

6.6. Summary

Acknowledgment

References

7. On the Definition of Cluster-Speci¯c Information Loss Measures V. Torra

Contents

7.1. Introduction

7.2. Preliminaries

7.2.1. Protection methods

7.2.2. Generic information loss measures

7.2.3. Fuzzy sets, fuzzy partitions, and fuzzy clustering

7.3. Information loss measures for clustering

7.3.1. Comparison of crisp clusters

7.3.2. Comparison of fuzzy clusters

7.3.3. Extensions using intuitionistic fuzzy sets

7.4. Conclusions and future work

Acknowledgments

References

8. Privacy Preserving and Use of Medical Information in a Multiagent System K. Gibert, A. Valls, L.

Contents

8.1. Introduction

8.2. Privacy preserving and security in a distributed platform for medical domains

8.3. Identification and authentication

8.4. Authorization and information access rights

8.4.1. Ontologies

8.4.2. Actor Profile Ontologies

8.5. Multiagent system

8.6. Intermediate layer for knowledge-interface communications

8.7. Private data protection

8.8. A real case: the K4Care project

8.8.1. The K4Care model

8.8.2. The knowledge management

8.8.3. The K4Care system architecture

8.9. Discussion

References

PART 3: Security by means of Artificial Intelligence

9. Perimeter Security on Noise-Robust Vehicle Detection Using Nonlinear Hebbian Learning B. Lu, A. D

Contents

9.1. Introduction

9.2. Description of the Proposed System

9.3. Unsupervised Nonlinear Hebbian Learning

9.3.1. Linear Hebbian Learning

9.3.2. Nonlinear Hebbian Learning

9.3.3. Nonlinear Activation Function

9.4. Real-time Field Testing Results

9.5. Simulation Results

9.5.1. Decision I: Vehicle vs. Non-vehicle Recognition

9.5.2. Decision II: Vehicle Type Identi¯cation

9.6. Conclusion and Discussion

Acknowledgment

References

10. Texture-Based Approach for Computer Vision Systems in Autonomous Vehicles D. Puig, J. Melendez a

Contents

10.1. Introduction

10.2. Background

10.3. Per-Pixel Texture Classifier

10.3.1. Feature Extraction

10.3.2. Texture Model Reduction

10.3.3. K-Nearest Neighbors Classification

10.3.4. Post-Processing

10.4. Automatic Parameter Selection

10.5. Experimental Results

10.6. Conclusions and Future Work

Acknowledgements

References

11. An Aggression Detection System for the Train Compartment Z. Yang, S. Fitrianie, D. Datcu and L.

Contents

11.1. Introduction

11.2. Related work

11.2.1. Automated aggression detection

11.2.2. Human based event reporting

11.3. System overview

11.4. Knowledge representation

11.4.1. Motivation

11.4.2. Ontology overview

11.4.3. The static context

11.4.4. Dynamic context

11.5. Automated aggression detection

11.5.1. Approach

11.5.2. Fusion and classification

11.5.2.1. Facial expression recognition

11.5.2.2. Emotion recognition from speech

11.5.2.3. Results for the extraction of emotion-related features

11.5.2.4. Event and activity recognition

11.5.3. Reasoning model

11.5.4. Implementation

11.6. Icon-based reporting tool on smart phones

11.6.1. The icon interface

11.6.2. System knowledge representation

11.7. Communication framework

11.8. The operator room

11.8.1. Icon language message interpreter

11.8.1.1. Multiple messages processor

11.9. Evaluation

11.10. Conclusions and future work

References

12. K-Means Clustering for Content-Based Document Management in Intelligence S. Decherchi, P. Gastal

Contents

12.1. Introduction

12.2. Document Clustering in Text Mining for Security Applications

12.2.1. Document indexing

12.2.2. Document clustering

12.3. Hybrid Approach to k-Means Clustering

12.3.1. Document distance measure

12.3.1.1. Algorithm for generating v00(D)

12.3.2. Kernel k-means

12.3.2.1. The feature-space version of k-means clustering

12.4. The Document-Clustering Framework

12.4.1. The document-clustering algorithm

12.4.1.1. The document-clustering procedure

12.4.2. Dimension reduction for document clustering by using random projections

12.4.3. Computational complexity

12.5. Experimental Results

12.5.1. Reuters-21578

12.5.2. Enron dataset

12.6. Conclusions

References

13. Genetic Algorithms for Designing Network Security Protocols L. Zarza, J. Forn¶e, J. Pegueroles

Contents

13.1. Introduction

13.2. Genetic algorithms

13.2.1. Definitions and terminology

13.2.2. General characteristics of genetic algorithms

13.2.3. Search space

13.2.4. Operation of a simple genetic algorithm

13.2.4.1. Selection phase

13.2.4.2. Modification phase

13.2.4.3. Evaluation phase

13.2.5. Genetic algorithms and learning

13.3. Security protocols

13.3.1. Conventions

13.4. State of art

13.4.1. State exploration

13.4.2. Belief logic

13.4.3. Genetic programming

13.5. Genome definition and interpretation

13.5.1. The binary sequence

13.5.1.1. Sender and receiver

13.5.1.2. Data

13.5.1.3. Keys

13.5.1.4. Structure

13.5.2. From the binary sequence to the genome

13.5.2.1. Genome structure

13.5.2.2. Genome interpretation

13.5.3. Analysis for genome construction

13.6. Security protocol evaluation: towards the ¯tness function

13.6.1. Aspects to evaluate

13.6.1.1. Number of goals achieved

13.6.1.2. Leaked data

13.6.1.3. Number of data acquired redundantly

13.6.1.4. Data acquired by keys received later than the data

13.6.1.5. Number of messages in the protocol

13.6.1.6. Transmission of large and small messages

13.6.1.7. Public and symmetric keys

13.6.1.8. Encoding large and small messages

13.6.2. Detecting the elements to be evaluated

13.6.3. Setting the weight of each element to be evaluated

13.6.4. Definition of proper values for weights

13.6.5. Applied values and their results

13.6.5.1. Example 1

13.6.5.2. Example 2

13.7. Conclusions

References

14. Evolving Strategy-Based Cooperation in Wireless Mobile Ad Hoc Networks M. Seredynski, P. Bouvry

Contents

14.1. Introduction

14.2. Cooperation enforcement system

14.2.1. Assumptions and performance metrics

14.2.2. Reputation system

14.2.3. Selection of best paths: path rating mechanism

14.2.4. Response mechanism: forwarding strategy

14.2.5. Packet Forwarding Game

14.2.6. Evaluation of strategies

14.2.7. Scheme of the evolutionary approach for analysis of behavior of the network

14.2.8. Underlying mechanisms

14.3. Computational experiments

14.3.1. Types of players in the NTS

14.3.2. Conditions of experiments

14.3.3. Results

14.4. Conclusions

People also search for Advances in Artificial Intelligent for Privacy Protection and Security 1st Edition:

artificial intelligence privacy

artificial intelligence privacy laws

artificial intelligence privacy issues

artificial intelligence privacy risks