Programme Parameters
Graduate / Intermediate
3 Days (4.5 Hrs)
Online (e-LMS)
• A basic understanding of the subject area and fundamental programming or scientific concepts.
• A laptop or desktop with a stable internet connection.
• Willingness to complete assignments and the capstone project.
About This Course
AI for Cybersecurity: Threat Detection and Risk Mitigation shows how machine learning strengthens defence across the security stack. You learn to build models that detect intrusions, malware and anomalous behaviour across networks, endpoints and identities, and to move from detection to risk: prioritising what matters, and informing mitigation. The course also covers the adversarial reality — attackers evading and targeting ML — and the balance of automation and human judgement. You finish able to apply AI to detect threats and reduce cyber risk. A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
🎯 Program Aim
This course applies AI to cybersecurity — threat detection, risk assessment and mitigation using machine learning across networks, endpoints and identities.
📋 Course Objectives
1. Detect intrusions and malware with ML.
2. Spot anomalous behaviour across the stack.
3. Prioritise and assess cyber risk.
4. Inform and drive mitigation.
5. Account for adversarial threats to ML.
👥 Who Should Enroll?
• Security analysts and engineers
• Risk and SOC professionals
• Security data scientists
• Students of cybersecurity
🚀 Key Learning Outcomes
• The ability to apply AI to threat detection.
• A detection-and-risk project.
• A risk-driven security approach.
• A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
💎 What You'll Gain
Live & Recorded Sessions
Lifetime access to class recordingse-Certificate on Completion
Cryptographically verified credentialPost-Programme Support
Direct access to mentors & councilHands-On Experience
Notebooks, real-world code & datasetsCurriculum Outline
Security Data and Its Limits
• Endpoint, network and identity telemetry: coverage gaps and blind spots
• Mapping detections to MITRE ATT&CK techniques rather than tool alerts
• Log normalisation, enrichment and the cost of retention decisions
Anomaly and Behavioural Analytics
• Baselining user and entity behaviour, and handling legitimate change
• Supervised detection where labels exist; unsupervised where they do not
• Beaconing, lateral movement and exfiltration signatures in practice
• Alert fatigue as the primary failure mode of security analytics
Attacks Against the Models Themselves
• Evasion of malware and phishing classifiers
• Data poisoning of models trained on customer telemetry
• Prompt injection and data exfiltration through LLM-based tooling
Triage, Automation and Containment
• Risk scoring and alert triage that preserves analyst judgement
• SOAR playbooks and choosing what is safe to automate
• Measuring detection engineering: time to detect, time to contain, coverage
Risk Mitigation and Assurance
• Threat modelling for AI-enabled systems and their supply chain
• Purple-team validation of detections against live technique emulation
• Reporting risk reduction in terms an executive can act on
Technical Specifications
| Parameter | Requirement |
|---|---|
| Covered Tool / Platform | Python |
| Covered Tool / Platform | TensorFlow |
| Covered Tool / Platform | PyTorch |
| Covered Tool / Platform | Keras |
| Covered Tool / Platform | Scikit-learn |
| Covered Tool / Platform | Jupyter Notebook |
| Covered Tool / Platform | Google Colab |
| Covered Tool / Platform | Hugging Face |
Frequently Asked Questions
Scholar Feedback & Reviews
Based on 0 scholar submissions
Rating Breakdown
No verified reviews published yet. Be the first to share your academic experience.
Leave Scholar Feedback
Your rating will help prospective scholars. Ratings below 3 stars are routed privately to the faculty mentor for immediate response.
