Intelligent Security Systems. Leon Reznik

3.15 Training time versus the size of the training set for RBF.Figure 3.16 Investigation of crossover operator choice and the number of gen...Figure 3.17 Investigation of mutation mechanisms.Figure 3.18 Investigation of ES systems.Figure 3.19 Perfect versus good neural networks.Figure 3.20 Employees number vs. attack detection error rate.Figure 3.21 Adaptability vs. attack classification error rate.Figure 3.22 Screenshot of SNORT configuration validation.Figure 3.23 Suricata interface view.Figure 3.24 Zeek interface view.

      5 Chapter 4Figure 4.1 Malware history timeline.Figure 4.2 Copy of the screenshot produced by Christma virus on the victim's...Figure 4.3 Malware classification scheme.Figure 4.4 Virus classification.Figure 4.5 Polymorphic engine controls virus execution and mutation.Figure 4.6 Metamorphic virus operation.Figure 4.7 Scanning techniques used by worms for self‐propagation.Figure 4.8 Trojan horses classification.Figure 4.9 Ransomware history timeline.Figure 4.10 Rootkits classification.Figure 4.11 Ensemble classifier architecture.Figure 4.12 A generic time‐based MLP. The inputs are previous values of the ...Figure 4.13 MTBMLP structure with three behavioral signals (X, Y, Z) used as...Figure 4.14 Multiple behavior signals change detection.Figure 4.15 Popular Windows anti‐malware tools market share.Figure 4.16 Diverse file scan modes. (a) The case of virus embedded in the m...

      6 Chapter 5Figure 5.1 The late Ralph Barclay shows off his box in 2009.Figure 5.2 Relationship between professional hackers’ groups.Figure 5.3 Hacker’s classification attempt.Figure 5.4 Phases of typical hacker’s activities.Figure 5.5 Advanced Port Scanner tool GUI (https://www.advanced‐port‐scanner...Figure 5.6 Hacker’s attacks scheme and their detection system.Figure 5.7 Colluded application attack data flow model.Figure 5.8 Recordings of the technological signals and their change during t...Figure 5.9 Basic architecture for a simple RNN model.Figure 5.10 Basic architecture for an LSTM model.Figure 5.11 LSTM model parameters generated by Tensor‐Flow.Figure 5.12 Basic architecture for a GRU model.Figure 5.13 GRU model parameters generated by Tensor‐Flow.Figure 5.14 Loss function plot from GRU versus LSTM using preprocessed datas...Figure 5.15 Loss function plot from GRU versus LSTM using raw dataset.Figure 5.16 Detection accuracy of both GRU and LSTM models that use preproce...Figure 5.17 Detection accuracy of both GRU and LSTM models that use raw data...Figure 5.18 Android application screenshots.Figure 5.19 Major occupation representations in survey respondents.Figure 5.20 Antimalware usage in the selected occupations.Figure 5.21 Virus and malware infection reports from selected respondent occ...Figure 5.22 Relative risk of password protection.Figure 5.23 Relative risk of reused passwords.Figure 5.24 Mobile device security evaluation structure.Figure 5.25 Membership functions for input representing OS version.Figure 5.26 Membership functions for Device Feature Security output.Figure 5.27 Authentication system structure and operation.Figure 5.28 KeyCollector utility GUI.Figure 5.29 Major primary typing features.Figure 5.30 The TOR website fingerprinting threat model.Figure 5.31 The WF attack workflow: the black arrow represents the processes...Figure 5.32 DF attack model architecture.Figure 5.33 Attack model performance (closed‐world scenario).Figure 5.34 Visual explanation of extend bursts and break bursts padding. Th...

      7 Chapter 6Figure 6.1 AML taxonomy of attacks, defenses, and consequences – from.Figure 6.2 Adversarial machine learning attack taxonomy.Figure 6.3 Adversarial machine learning attack classification.Figure 6.4 Accuracy degradation plot for J48 with missing values induction....Figure 6.5 Accuracy degradation plot for random forest with missing values i...Figure 6.6 Accuracy degradation plot for J48 with invalid values induction....Figure 6.7 Accuracy degradation plot for Random Forest with invalid values i...Figure 6.8 Accuracy degradation plot for J48 with errors induction.Figure 6.9 Accuracy degradation plot for Random Forest with errors induction...Figure 6.10 Basic GAN structure.Figure 6.11 GAN with generator G, which generates images, and discriminator Figure 6.12 Semi‐supervised GAN can be used not only with labeled data in su...Figure 6.13 GAN minimax loss has opposite ideal conditions for each of the n...Figure 6.14 Performance comparison of conventional classifier versus semi‐su...Figure 6.15 Performance comparison of conventional classifier VS semi‐superv...

      Guide

      1  Cover Page

      2  Series Page

      3  Title Page

      4  Copyright Page

      5  Dedication Page

      6  Acknowledgments

      7  Introduction

      8  Table of Contents

      9  Begin Reading

      10  Index

      11  Wiley End User License Agreement

      Pages

      1  ii

      2  iii

      3  iv

      4  ix

      5  xi

      6  xii

      7  xiii

      8  xiv

      9  xv

      10  xvi

      11  xvii

      12  xviii

      13  xix

      14  xx

      15  xxi

      16  xxii

      17  xxiii

      18  xxiv

      19  xxv

      20  xxvi