Torrent details for "Santos O., Radanliev P. AI-Powered Digital Cyber Resilience 2025" Log in to bookmark
Controls:
×
Report Torrent
Please select a reason for reporting this torrent:
Your report will be reviewed by our moderation team.
×
Report Information
Loading report information...
This torrent has been reported 0 times.
Report Summary:
| User | Reason | Date |
|---|
Failed to load report information.
×
Success
Your report has been submitted successfully.
Checked by:
Category:
Language:
None
Total Size:
5.9 MB
Info Hash:
90827A5760078E2B0A4C3EF248D1BCAF78494B6C
Added By:
Added:
Sept. 23, 2025, 11:36 a.m.
Stats:
|
(Last updated: Sept. 23, 2025, 11:39 a.m.)
| File | Size |
|---|---|
| Santos O., Radanliev P. AI-Powered Digital Cyber Resilience 2025.pdf | 5.9 MB |
Name
DL
Uploader
Size
S/L
Added
-
11.5 MB
[10
/
3]
2023-11-27
| Uploaded by indexFroggy | Size 11.5 MB | Health [ 10 /3 ] | Added 2023-11-27 |
-
34.4 MB
[16
/
3]
2023-12-07
| Uploaded by indexFroggy | Size 34.4 MB | Health [ 16 /3 ] | Added 2023-12-07 |
-
29.2 MB
[61
/
1]
2024-12-29
| Uploaded by indexFroggy | Size 29.2 MB | Health [ 61 /1 ] | Added 2024-12-29 |
-
615.8 MB
[31
/
20]
2024-10-03
| Uploaded by XXXClub | Size 615.8 MB | Health [ 31 /20 ] | Added 2024-10-03 |
NOTE
SOURCE: Santos O., Radanliev P. AI-Powered Digital Cyber Resilience 2025
-----------------------------------------------------------------------------------
COVER
-----------------------------------------------------------------------------------
MEDIAINFO
Textbook in PDF format The Future of Cybersecurity Is Her--And It's Intelligent. AI Powered Digital Cyber Resilience delivers an essential guide for understanding how artificial intelligence is transforming the world of cybersecurity. As cyber threats become more sophisticated and persistent, traditional defenses are no longer enough. This groundbreaking book explores how AI technologies--including Generative AI, large and small language models (LLMs and SLMs), and real-time anomaly detection--can detect, prevent, and respond to cyber threats faster and more accurately than ever before. Designed for IT and security professionals, students, academics, and decision-makers, this book bridges theory and practice with clarity and depth. From foundational AI concepts to advanced threat intelligence, automated incident response, and securing AI itself, this is your playbook for building resilient digital systems in an era of intelligent threats. Reinforcement learning represents another critical dimension within the AI systems, where an agent learns to make decisions by interacting with an environment and receiving feedback in the form of rewards or penalties. This approach is highly applicable in adaptive security systems, where continuous learning and adaptation to evolving threats are essential. Q-learning, a model-free reinforcement learning algorithm, is widely employed in developing autonomous intrusion detection systems that dynamically adjust their strategies based on the network environment’s behavior. The integration of Q-learning with deep learning, as seen in Deep Q-Networks (DQNs), further enhances the agent’s capability to navigate complex environments, such as those encountered in large-scale, multilayered network infrastructures. Deep Learning, particularly through neural networks, introduces advanced methodologies for processing vast and complex datasets in cybersecurity. Convolutional neural networks (CNNs) are extensively applied in tasks requiring spatial feature extraction, such as analyzing visual data from security camera feeds or detecting malware embedded in images. CNNs use convolutional layers to automatically detect spatial hierarchies within data, rendering them effective in identifying subtle, image-based threats that might elude traditional detection methods. Recurrent neural networks (RNNs), and more specifically long short-term memory (LSTM) networks, are designed to handle sequential data, making them particularly well suited for analyzing time-series data in cybersecurity contexts. The capacity of LSTM networks to remember long-term dependencies allows them to model the temporal evolution of network traffic, which is instrumental in predicting and preempting cyber threats based on historical attack patterns. For instance, LSTMs can detect patterns that precede a distributed denial-of-service (DDoS) attack, thus enabling proactive mitigation. The transformer architecture, which underpins large language models (LLMs) like GPT-4o, represents a significant advancement in natural language processing (NLP) and has profound implications for cybersecurity. Transformers, with their ability to process sequences of data in parallel, are highly efficient in tasks such as the real-time analysis of security logs and the automated extraction of threat intelligence. This capability is particularly valuable in cybersecurity, where vast amounts of unstructured data from threat reports, logs, and social media can be parsed and analyzed in real time, thereby enabling organizations to swiftly respond to emerging threats. Preface Introduction Understanding Digital Cyber Resilience in the Age of AI Introduction to Generative AI, LLMs, and SLMs Anomaly Detection, Predictive Analysis, and Threat Forecasting AI-Driven Threat Intelligence Introduction to AI-Driven Incident Response Real-Time Analysis, Decision Making, Orchestration and Automation IoT Security and Cloud Security Using AI Advanced Encryption Techniques, Privacy, and Compliance Using AI to Enhance Cybersecurity Programs and Policies Securing AI Implementations
×