Cantitate/Preț
Produs
Total produse
Vezi coșul
Malware Analysis Using Artificial Intelligence and Deep Learning de Mark Stamp

Malware Analysis Using Artificial Intelligence and Deep Learning

Editat de Mark Stamp, Mamoun Alazab, Andrii Shalaginov
en Limba Engleză Paperback – 21 dec 2021

Considerăm că volumul Malware Analysis Using Artificial Intelligence and Deep Learning reprezintă o resursă tehnică esențială, concentrată pe implementarea algoritmilor de Deep Learning (DL) și Inteligență Artificială (AI) în securitatea cibernetică contemporană. Lucrarea se distinge prin abordarea „data-driven”, demonstrând cum modelele avansate pot identifica amenințări complexe cu o intervenție minimă din partea experților umani în domeniul malware-ului tradițional. Notăm cu interes integrarea unor tehnologii de ultimă oră, precum Word2Vec și HMM2Vec, utilizate pentru transformarea codului malițios în vectori procesabili, facilitând astfel o clasificare precisă.

Structura cărții este riguros organizată pe 13 capitole ce progresează de la fundamentele clasificării statice a fișierelor binare către aplicații ultraspecializate. Observăm o atenție deosebită acordată mediilor emergente, volumul explorând securitatea vehiculelor autonome și analiza comportamentală în Cloud IaaS. Complementar volumului Cyber Malware de Iman Almomani, care oferă o bază teoretică despre vectorii de atac, această lucrare se concentrează pe mecanismele interne de procesare a datelor și pe instrumentele de dezvoltare necesare inovației în cercetare.

În contextul operei editorului Mark Stamp, acest titlu extinde conceptele din Introduction to Machine Learning with Applications in Information Security, trecând de la o introducere academică la studii de caz avansate și tehnici de nișă precum sentiment analysis pentru detecția trollilor. Prin comparație cu Artificial Intelligence for Cybersecurity, volumul de față pune un accent mai mare pe latura practică a analizei malware-ului, oferind cercetătorilor cadrele de lucru necesare pentru a aborda peisajul în continuă schimbare al amenințărilor cibernetice.

Citește tot Restrânge

Preț: 113046 lei

Preț vechi: 141307 lei
-20%

Puncte Express: 1696
Paperback 113046 lei
Hardback 113696 lei

Carte tipărită la comandă

Livrare economică 15-29 iunie

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9783030625849
ISBN-10: 3030625842
Pagini: 651
Ilustrații: XX, 651 p. 253 illus., 209 illus. in color.
Dimensiuni: 155 x 235 mm
Greutate: 0.93 kg
Ediția:1st ed. 2021
Editura: Springer International Publishing
Colecția Springer
Locul publicării:Cham, Switzerland

De ce să citești această carte

Recomandăm această carte profesioniștilor în securitate cibernetică și cercetătorilor care doresc să treacă de la analiza tradițională la metode automatizate bazate pe Deep Learning. Cititorul câștigă acces la metodologii riguroase pentru clasificarea malware-ului și detecția URL-urilor malițioase, fiind un ghid practic pentru implementarea AI în protecția infrastructurilor critice, precum vehiculele autonome sau sistemele cloud.

Despre autor

Mark Stamp este profesor de informatică la San Jose State University, unde coordonează cursuri de securitate a informației la nivel de licență și masterat. Expertiza sa este consolidată de o experiență de șapte ani ca criptanalist în cadrul National Security Agency (NSA) din SUA, precum și de activitatea sa în sectorul privat. Autor prolific, acesta a publicat lucrări fundamentale în domeniu, precum Applied Cryptanalysis și Machine Learning, Deep Learning and AI for Cybersecurity, fiind o autoritate recunoscută la intersecția dintre criptografie, machine learning și securitate cibernetică.

Descriere scurtă

​This book is focused on the use of deep learning (DL) and artificial intelligence (AI) as tools to advance the fields of malware detection and analysis. The individual chapters of the book deal with a wide variety of state-of-the-art AI and DL techniques, which are applied to a number of challenging malware-related problems. DL and AI based approaches to malware detection and analysis are largely data driven and hence minimal expert domain knowledge of malware is needed.

This book fills a gap between the emerging fields of DL/AI and malware analysis. It covers a broad range of modern and practical DL and AI techniques, including frameworks and development tools enabling the audience to innovate with cutting-edge research advancements in a multitude of malware (and closely related) use cases.

Cuprins

1. Optimizing Multi-class Classification of Binaries Based on Static Features.- 2.Detecting Abusive Comments Using Ensemble Deep Learning Algorithms.- 3. Deep Learning Techniques for Behavioural Malware Analysis in Cloud IaaS.- 4. Addressing Malware Attacks on Connected and Autonomous Vehicles: Recent Techniques and Challenges.- 5. A Selective Survey of Deep Learning Techniques and Their Application to Malware Analysis.- 6. A Comparison of Word2Vec, HMM2Vec, and PCA2Vec for Malware Classification.- 7. Word Embedding Techniques for Malware Evolution Detection.- 8. Reanimating Historic Malware Samples.- 9. DURLD: Malicious URL detection using Deep learning based Character-level representations.- 10. Sentiment Analysis for Troll Detection on Weibo.- 11. Beyond Labeling: Using Clustering to Build Network Behavioral Profiles of Malware Families.- 12. Review of the Malware Categorization in the Era of Changing Cybethreats Landscape: Common Approaches, Challenges and Future Needs.- 13. An Empirical Analysis of Image-Based Learning Techniques for Malware Classification.- 14. A Survey of Intelligent Techniques for Android Malware Detection.- 15. Malware Detection with Sequence-Based Machine Learning and Deep Learning.- 16. A Novel Study on Multinomial Classification of x86/x64 Linux ELF Malware Types and Families through Deep Neural Networks.- 17. Cluster Analysis of Malware Family Relationships.- 18. Log-Based Malicious Activity Detection using Machine and Deep Learning.- 19. Deep Learning in Malware Identification and Classification.- 20. Image Spam Classification with Deep Neural Networks.- 21. Fast and Straightforward Feature Selection Method.- 22. On Ensemble Learning.- 23. A Comparative Study of Adversarial Attacks to Malware Detectors Based on Deep Learning.- 24. Review of Artificial Intelligence Cyber Threat Assessment Techniques for Increased System Survivability.- 25. Universal Adversarial Perturbations and Image Spam Classifiers.

Notă biografică

Mark Stamp has extensive experience in information security and machine learning, having worked in these fields within academic, industrial, and government environments. After completing his PhD research in cryptography at Texas Tech University, he spent more than seven years as a cryptanalyst with the United States National Security Agency (NSA), followed by two years developing a digital rights management product for a Silicon Valley start-up company. Since 2002, Dr. Stamp has been a Professor in the Department of Computer Science at San Jose State University, where he teaches courses in machine learning and information security. To date, he has published more than 140 research papers, most of which deal with problems at the interface between machine learning and information security. Dr. Stamp served as co-editor of the Handbook of Information and Communication Security (Springer, 2010), and he is the author of four books, including a popular information security textbook(Information Security: Principles and Practice, 2nd edition, Wiley, 2011) and, most recently, a machine learning textbook (Introduction to Machine Learning with Applications in Information Security, Chapman and Hall/CRC, 2017).
Mamoun Alazab received his PhD degree in Computer Science from the Federation University of Australia, School of Science, Information Technology and Engineering. He is currently an Associate Professor in the College of Engineering, IT and Environment at Charles Darwin University, Australia. He is a cyber-security researcher and practitioner with industry and academic experience. Dr. Alazab's research is multidisciplinary, with a focus on cyber security and digital forensics of computer systems, including current and emerging issues in the cyber environment, such as cyber-physical systems and the Internet of Things. His research takes into consideration the unique challenges present in these environments, with an emphasis on cybercrime detection and prevention. He has a particular interest in the application of machine learning as an essential tool for cybersecurity, examples of which include detecting attacks, analyzing malicious code, and uncovering vulnerabilities in software.  He is the Founder and the Chair of the IEEE Northern Territory Subsection (February 2019 - present), a Senior Member of the IEEE, Cybersecurity Academic Ambassador for Oman's Information Technology Authority (ITA), and Member of the IEEE Computer Society's Technical Committee on Security and Privacy (TCSP). In addition, he has collaborated with government and industry on many projects, including work with IBM, Trend Micro, Westpac, the Australian Federal Police (AFP), the Australian Communications and Media Authority (ACMA), Westpac, UNODC to name a few.
Andrii Shalaginov is a Researcher in Information Security and Digital Forensics at the Department of Information Security and Communication Technology, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology (NTNU). Dr. Shalaginov was awarded the PhD degree in Information Security from NTNU in February 2018. During the last decade, Dr. Shalaginov's focus has been on the fields of cybercrime investigation and intelligent malware detection. His primary expertise is in static and dynamic malware analysis, development of machine learning-aided intelligent computer virus detection models, and similarity-based categorization of cyberattacks in the Internet of Things. Further, Dr. Shalaginov has worked as a security researcher for UNICRI/EUIPO on malware analysis for copyright-infringing websites. He was nominated as a representative from Norway at COST Action CA17124 "DigForAsp - Digital forensics: evidence analysis via intelligent systems and practices". In 2018, Dr. Shalaginov, together with his NTNU team, received an award for first place in the "Future of Smart Policing" hackathon competition sponsored by INTERPOL (Singapore). Dr. Shalaginov also holds a second Master's Degree in Information Security (Digital Forensics) from Gjøvik University College (GUC), and he received BSc and MSc degrees in System Designing from the National Technical University of Ukraine "Kyiv Polytechnic Institute", Department of Computer-Aided Design. Finally, Dr. Shalaginov is LE-1/LPIC-1 certified and has extensive industry experience, including work at Samsung R&D Center.

Caracteristici

Explores how deep learning and artificial intelligence can effectively be used in malware detection and analysis Showcases state-of-the-art tools, frameworks and techniques to enable readers to implement them Utilises numerous examples and cases in the field of cybersecurity and malware detection