Muutke küpsiste eelistusi

E-raamat: Machine Learning and Security: Protecting Systems with Data and Algorithms

3.62/5 (54 hinnangut Goodreads-ist)
,
  • Formaat: 386 pages
  • Ilmumisaeg: 26-Jan-2018
  • Kirjastus: O'Reilly Media
  • Keel: eng
  • ISBN-13: 9781491979853
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 47,96 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Machine Learning and Security: Protecting Systems with Data and AlgorithmsSuurem pilt
  • Formaat: 386 pages
  • Ilmumisaeg: 26-Jan-2018
  • Kirjastus: O'Reilly Media
  • Keel: eng
  • ISBN-13: 9781491979853
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Can machine learning techniques solve our computer security problems and finally put an end to the cat-and-mouse game between attackers and defenders? Or is this hope merely hype? Now you can dive into the science and answer this question for yourself. With this practical guide, youll explore ways to apply machine learning to security issues such as intrusion detection, malware classification, and network analysis.

Machine learning and security specialists Clarence Chio and David Freeman provide a framework for discussing the marriage of these two fields, as well as a toolkit of machine-learning algorithms that you can apply to an array of security problems. This book is ideal for security engineers and data scientists alike.

Learn how machine learning has contributed to the success of modern spam filters Quickly detect anomalies, including breaches, fraud, and impending system failure Conduct malware analysis by extracting useful information from computer binaries Uncover attackers within the network by finding patterns inside datasets Examine how attackers exploit consumer-facing websites and app functionality

Translate your machine learning algorithms from the lab to production Understand the threat attackers pose to machine learning solutions
Preface xi
1 Why Machine Learning and Security?
1(24)
Cyber Threat Landscape
3(4)
The Cyber Attacker's Economy
7(1)
A Marketplace for Hacking Skills
7(1)
Indirect Monetization
8(1)
The Upshot
8(1)
What Is Machine Learning?
9(1)
What Machine Learning Is Not
10(1)
Adversaries Using Machine Learning
11(1)
Real-World Uses of Machine Learning in Security
12(2)
Spam Fighting: An Iterative Approach
14(9)
Limitations of Machine Learning in Security
23(2)
2 Classifying and Clustering
25(54)
Machine Learning: Problems and Approaches
25(2)
Machine Learning in Practice: A Worked Example
27(5)
Training Algorithms to Learn
32(1)
Model Families
33(2)
Loss Functions
35(1)
Optimization
36(4)
Supervised Classification Algorithms
40(1)
Logistic Regression
40(2)
Decision Trees
42(3)
Decision Forests
45(2)
Support Vector Machines
47(2)
Naive Bayes
49(3)
k-Nearest Neighbors
52(1)
Neural Networks
53(2)
Practical Considerations in Classification
55(1)
Selecting a Model Family
55(1)
Training Data Construction
56(3)
Feature Selection
59(2)
Overfitting and Underfitting
61(1)
Choosing Thresholds and Comparing Models
62(3)
Clustering
65(1)
Clustering Algorithms
65(10)
Evaluating Clustering Results
75(2)
Conclusion
77(2)
3 Anomaly Detection
79(46)
When to Use Anomaly Detection Versus Supervised Learning
80(1)
Intrusion Detection with Heuristics
81(1)
Data-Driven Methods
82(3)
Feature Engineering for Anomaly Detection
85(1)
Host Intrusion Detection
85(4)
Network Intrusion Detection
89(3)
Web Application Intrusion Detection
92(1)
In Summary
93(1)
Anomaly Detection with Data and Algorithms
93(2)
Forecasting (Supervised Machine Learning)
95(11)
Statistical Metrics
106(1)
Goodness-of-Fit
107(5)
Unsupervised Machine Learning Algorithms
112(4)
Density-Based Methods
116(2)
In Summary
118(1)
Challenges of Using Machine Learning in Anomaly Detection
119(1)
Response and Mitigation
120(1)
Practical System Design Concerns
121(1)
Optimizing for Explainability
121(2)
Maintainability of Anomaly Detection Systems
123(1)
Integrating Human Feedback
123(1)
Mitigating Adversarial Effects
123(1)
Conclusion
124(1)
4 Malware Analysis
125(56)
Understanding Malware
126(2)
Defining Malware Classification
128(3)
Malware: Behind the Scenes
131(14)
Feature Generation
145(1)
Data Collection
146(1)
Generating Features
147(24)
Feature Selection
171(3)
From Features to Classification
174(4)
How to Get Malware Samples and Labels
178(1)
Conclusion
179(2)
5 Network Traffic Analysis
181(54)
Theory of Network Defense
183(1)
Access Control and Authentication
183(1)
Intrusion Detection
184(1)
Detecting In-Network Attackers
185(1)
Data-Centric Security
185(1)
Honeypots
186(1)
Summary
186(1)
Machine Learning and Network Security
187(1)
From Captures to Features
187(6)
Threats in the Network
193(4)
Botnets and You
197(6)
Building a Predictive Model to Classify Network Attacks
203(2)
Exploring the Data
205(5)
Data Preparation
210(4)
Classification
214(2)
Supervised Learning
216(6)
Semi-Supervised Learning
222(1)
Unsupervised Learning
223(5)
Advanced Ensembling
228(5)
Conclusion
233(2)
6 Protecting the Consumer Web
235(40)
Monetizing the Consumer Web
236(1)
Types of Abuse and the Data That Can Stop Them
237(1)
Authentication and Account Takeover
237(6)
Account Creation
243(5)
Financial Fraud
248(3)
Bot Activity
251(5)
Supervised Learning for Abuse Problems
256(1)
Labeling Data
256(2)
Cold Start Versus Warm Start
258(1)
False Positives and False Negatives
258(1)
Multiple Responses
259(1)
Large Attacks
259(1)
Clustering Abuse
260(1)
Example: Clustering Spam Domains
261(1)
Generating Clusters
262(4)
Scoring Clusters
266(5)
Further Directions in Clustering
271(1)
Conclusion
272(3)
7 Production Systems
275(40)
Defining Machine Learning System Maturity and Scalability
275(2)
What's Important for Security Machine Learning Systems?
277(1)
Data Quality
277(1)
Problem: Bias in Datasets
277(2)
Problem: Label Inaccuracy
279(1)
Solutions: Data Quality
279(1)
Problem: Missing Data
280(1)
Solutions: Missing Data
281(3)
Model Quality
284(1)
Problem: Hyperparameter Optimization
285(1)
Solutions: Hyperparameter Optimization
285(5)
Feature: Feedback Loops, A/B Testing of Models
290(3)
Feature: Repeatable and Explainable Results
293(4)
Performance
297(1)
Goal: Low Latency, High Scalability
297(1)
Performance Optimization
298(2)
Horizontal Scaling with Distributed Computing Frameworks
300(5)
Using Cloud Services
305(2)
Maintainability
307(1)
Problem: Checkpointing, Versioning, and Deploying Models
307(2)
Goal: Graceful Degradation
309(1)
Goal: Easily Tunable and Configurable
309(1)
Monitoring and Alerting
310(2)
Security and Reliability
312(1)
Feature: Robustness in Adversarial Contexts
312(1)
Feature: Data Privacy Safeguards and Guarantees
312(1)
Feedback and Usability
313(1)
Conclusion
314(1)
8 Adversarial Machine Learning
315(28)
Terminology
316(1)
The Importance of Adversarial ML
317(1)
Security Vulnerabilities in Machine Learning Algorithms
318(2)
Attack Transferability
320(2)
Attack Technique: Model Poisoning
322(3)
Example: Binary Classifier Poisoning Attack
325(5)
Attacker Knowledge
330(1)
Defense Against Poisoning Attacks
331(2)
Attack Technique: Evasion Attack
333(1)
Example: Binary Classifier Evasion Attack
334(5)
Defense Against Evasion Attacks
339(1)
Conclusion
340(3)
A Supplemental Material for
Chapter 2		 343(8)
B Integrating Open Source Intelligence 351(4)
Index 355
Clarence Chio has a B.S. and M.S. in Computer Science from Stanford, specializing in data mining and artificial intelligence. He has spoken on machine learning and/or security at DEF CON and 11 other infosec/software engineering conferences in 8 countries between 2015 and 2016. He had been a community speaker with Intel, and a security consultant for Oracle. Clarence currently works as a Security Research Engineer at Shape Security, building a product that protects high valued web assets from automated attacks. He is also the founder and organizer of the "Data Mining for Cyber Security" meetup group, the largest gathering of security data scientists in the San Francisco Bay Area.David Freeman is head of Anti-Abuse Relevance at LinkedIn, where he leads a team of machine learning engineers charged with detecting and preventing fraud and abuse across the LinkedIn site and ecosystem. He has a Ph.D. in mathematics from UC Berkeley and did postdoctoral research in cryptography and security at CWI and Stanford University.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97814919798536e.html
Märksõnad: