📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of AI in Digital Forensics, from foundations to a certified capstone project.
Foundations
• Chain of custody, forensic imaging and write-blocking fundamentals
• Admissibility standards and the expert's duty to the court
• Where an automated finding must still be humanly verifiable to be usable
Triage
• Classification and clustering to triage terabyte-scale seizures
• Known-file filtering, hash sets and perceptual hashing for near-duplicates
• Precision and recall trade-offs when a missed artefact is a missed crime
Media
• Source attribution: sensor pattern noise and compression fingerprints
• Manipulation and deepfake detection, and the fragility of current detectors
• Speaker and face recognition evidence: error rates and demographic disparity
Text & Network
• Authorship attribution and its limits with short, informal text
• Anomaly detection over network and endpoint telemetry
• Timeline reconstruction across heterogeneous, clock-skewed sources
Practice
• Explaining a model-derived finding to a non-technical trier of fact
• Validation records, error rates and the questions opposing counsel will ask
• Bias, provenance of training data, and grounds on which AI evidence is challenged
Earn government-registered certification in AI in Digital Forensics
e-Certificate and e-Marksheet issued on successful completion.
