Machine Learning Techniques and Analytics for Cloud Security. Группа авторов

Читать онлайн книгу.

Machine Learning Techniques and Analytics for Cloud Security - Группа авторов


Скачать книгу
4.6 Block diagram for fitness tracking using Google Fit.Figure 4.7 Implementation of PIR sensor in our system.Figure 4.8 Block diagram of the control unit.Figure 4.9 Live streaming results of the LDR sensor.Figure 4.10 API keys operational workbook.Figure 4.11 API graphs from Google Cloud Console.Figure 4.12 API data call counter log.Figure 4.13 API data push and pull traffic data graph.

      5 Chapter 5Figure 5.1 Diagram of ANN [5].Figure 5.2 State diagram of Mealy machine [26].Figure 5.3 ANN structure [27].Figure 5.4 Flow chart of our proposed technique.Figure 5.5 Histogram analysis [27].Figure 5.6 Graph of Table 5.3.Figure 5.7 Graph of Table 5.4.

      6 Chapter 6Figure 6.1 Intrusion detection system in a nutshell.Figure 6.2 (a) Basic architecture of intrusion detection system (IDS).Figure 6.2 (b) Basic architecture of intrusion prevention system (IPS).Figure 6.3 The flowchart of the proposed IDS used in this work.

      7 Chapter 7Figure 7.1 A block diagram of the proposed mood-based sentiment analysis and the...Figure 7.2 Confusion matrices for Bayes, Gradient Descent with five neuron, and ...Figure 7.3 Confusion matrices for ADAM Optimizer with 5 neuron, ADAM Optimizer w...Figure 7.4 Performance of the proposed Naïve Bayes, Adam5, Adam10, GD5, GD10, an...Figure 7.5 Performance of the proposed Naïve Bayes, ADAM5, ADAM10, GD5, GD10 and...Figure 7.6 Performance of the proposed Naïve Bayes, ADAM5, ADAM10, GD5, GD10, an...Figure 7.7 Performance of the proposed Naïve Bayes, ADAM5, ADAM10, GD5, GD10, an...

      8 Chapter 8Figure 8.1 Requirement of cloud security.Figure 8.2 Fiat-Shamir protocol.Figure 8.3 Diffie-Hellman key exchange algorithm.Figure 8.4 ZKP version 1 [17].Figure 8.5 ZKP Version 2 [17].Figure 8.6 Cloud architecture.

      9 Chapter 9Figure 9.1 Components of a communication.Figure 9.2 An example of malicious spam message.Figure 9.3 Flowchart of spam filtered communication system.Figure 9.4 Overview of the system.Figure 9.5 A sample spam message in regional language typed in English.Figure 9.6 A sample spam message in regional language typed in English.Figure 9.7 Architecture of designed CNN classifier.Figure 9.8 Illustrative example of the k-fold cross-validation technique.Figure 9.9 Mean of mean accuracies of the different classification models.Figure 9.10 Mean of mean F1 scores of the different classification models.Figure 9.11 Statistical distribution of classifier performance in terms of mean ...Figure 9.12 Statistical distribution of classifier performance in terms of mean ...Figure 9.13 Illustration of the proposed CNN-based model in cloud architecture.

      10 Chapter 10Figure 10.1 Phishing websites in Q1 and Q2, 2020.Figure 10.2 Feature extraction.Figure 10.3 Workflow diagram of phishing detection.Figure 10.4 Working of logistic regression.Figure 10.5 Working of voting classification.Figure 10.6 Phishing URL classification process.Figure 10.7 Comparison of accuracy scores.Figure 10.8 Comparison of precision scores.Figure 10.9 Comparison of recall scores.Figure 10.10 Comparison of F1 scores.

      11 Chapter 11Figure 11.1 Cloud computing architecture.Figure 11.2 Entity responsible for the maintenance of cloud system resources.Figure 11.3 Honeypot system diagram.Figure 11.4 Blockchain architecture.Figure 11.5 Yugala architecture.

      12 Chapter 12Figure 12.1 Block diagram.

      13 Chapter 13Figure 13.1 Blind spots in neural networks (source: Szegedy et al. [11]).Figure 13.2 Representing a decision boundary with two classes separated by it.Figure 13.3 Panda image with initial probabilities and final probabilities.Figure 13.4 Example of adversarial effect on panda image (source: Goodfellow et ...Figure 13.5 Example of adversarial effect on word (source: Zang et al. [20]).Figure 13.6 Overview of FeatureFool framework [48]. (a) generate unlabeled datas...

      14 Chapter 14Figure 14.1 Homomorphic encryption in clouds.Figure 14.2 Searchable encryption in clouds.Figure 14.3 Ciphertext-policy attribute-based encryption in clouds.Figure 14.4 Two-party encryption.Figure 14.5 Wotrkflow of encryption checking.Figure 14.6 Sever-side deduplication.Figure 14.7 Workflow of integrity checking.Figure 14.8 Client-side deduplication.Figure 14.9 Workflow of replication checking.Figure 14.10 Workflow of proofs of co-residence.Figure 14.11 Geolocation of data in clouds.

      15 Chapter 15Figure 15.1 Current top 4 public cloud provider’s growth over one year span. (So...Figure 15.2 How RPCs work. User requests to access Service 2 through Service 1.Figure 15.3 Structure of an IAM policy.Figure 15.4 Sub-account billing method.Figure 15.5 The flow of IAP verification.Figure 15.6 How event threat detection works.Figure 15.7 Hot potato, used by other cloud providers like AWS and Azure.Figure 15.8 Cold potato, available in the premium network tier of GCP.

      16 Chapter 16Figure 16.1 Data encryption at rest.Figure 16.2 Data encryption at transit.Figure 16.3 Implementation of encryption keys in Azure.Figure 16.4 Working of Azure API.Figure 16.5 Virtual Machine.Figure 16.6 Working of Blob Storage.Figure 16.7 Working of CDN.Figure 16.8 Key features of CDN.Figure 16.9 Defense in depth.Figure 16.10 Working of conditional access.Figure 16.11 Functions of Azure Sentinel.

      17 Chapter 17Figure 17.1 Consumer acquisition of Nutanix from 2017 to 2020 (Source: Blocks an...Figure 17.2 Revenue trends of Nutanix (NTNX) over the period of 2014 to 2020. Th...Figure 17.3 Nutanix Hybrid Cloud’s Hyperconverged Infrastructure (HCI).Figure 17.4 Prism control plane segments.Figure 17.5 Acropolis and associated segments.Figure 17.6 Nutanix DR constructs’ hierarchy in distributed storage fabric.Figure 17.7 Nutanix Cerebro Service functioning.Figure 17.8 (a) Default unsegmented network. (b) Segmented network.

      18 Chapter 18Figure 18.1 Main methodology to generate APCs from an interaction network.Figure 18.2 Example of a community partitioned into subcommunities and k-shells.Figure 18.3 Bottom-up merger strategy. Keep one, keep the ones above the thresho...Figure 18.4 Merge and simplification of two ACPs in DNF model.Figure 18.5 Overview of WSC landscape for ACPs from 1 to 13 clauses and attribut...Figure 18.6 An illustrative example of the confusion matrix for a binary model.Figure 18.7 Distribution of the similarity values between pairs of nodes assigne...Figure 18.8 Histogram of the average number of selected edges for 31 executions ...Figure 18.9 Results of the accuracy metric using the two evaluation approaches a...Figure 18.10 Average behavior of the precision, recall, F1 score, and accuracy m...

      19 Chapter 19Figure 19.1 Basic approaches in Artificial Intelligence.Figure 19.2 Possible programs on AI, ML, and Robotics at iSchools.Figure 19.3 Number of programs on AI, ML, and Robotics.

      List of Table

      1 Chapter 1Table 1.1 Comparison between AWS Outpost, Microsoft Azure Stack, and Google Clou...Table 1.2 Pros and cons between AWS Outpost, Microsoft Azure Stack, and Google C...Table 1.3 Comparison between VMware Microsoft Amazon AWS.

      2 Chapter 2Table 2.1 Significant glycan list.Table 2.2 The tabular format has been created from the above diagram.Table 2.3 Performance of the method using various metrices.

      3 Chapter 3Table 3.1 Resultant genes (gene symbols) identified by PC-LR method.Table 3.2 Resultant genes (gene symbols) identified by PC-LR method.

      4 Chapter 5Table 5.1 Mealy machine.Table 5.2 Specifications of H/w and S/w used in the experiment.Table 5.3 Serial test.Table 5.4 Avalanche effect: change in session key.Table 5.5 Input vector and initial weight vectors.Table 5.6 Updated weight vectors.Table 5.7 Comparison between coupled TPM and coupled feedforward ANN.Table 5.8 Comparison table.

      5 Chapter 6Table 6.1 Comparative table of NIDS and HIDS.Table 6.2 Comparative table of signature-based and anomaly-based IDS.Table 6.3 Some of the works pertaining to IDS in recent years.Table 6.4 (a) The accuracies yielded through various state-of-the-art classifier...Table 6.4 (b) The accuracies yielded through various state-of-the-art classifier...Table 6.4 (c) The accuracies yielded through various state-of-the-art classifier...Table 6.5 The accuracies yielded through various state-of-the-art classifiers im...

      6 Chapter 7Table 7.1 Performance in different indexes.

      7 Chapter


Скачать книгу