Investigation - ML classification - Web security
Selected projects
Three projects that show PFA readiness.
Each case is presented by problem, method and relevance: cyber investigation, machine-learning classification and security testing for user-facing platforms.
Log investigation / Splunk
Intrusion reconstruction from security logs
Reconstructed a Volt Typhoon-style intrusion from Windows and application logs, then organized the result into a readable timeline with indicators and detection queries.
- Mapped attacker behavior across account takeover, command execution, persistence, credential access and cleanup.
- Used Splunk searches and event correlation to move from raw logs to an incident narrative.
- Relevant to cyber reporting, signal triage and clear technical restitution.
SplunkIOCTimeline
Applied ML / Risk classification
Fault classification prototype from sensor data
Built a Python prototype that classifies pump fault risk from sensor values and presents the result through a simple desktop interface.
- Prepared data with Pandas and trained a Random Forest classifier with Scikit-learn.
- Translated model output into a readable risk level for the user.
- Useful pattern for AI/Data internships: data preparation, classification workflow and explainable output.
PythonScikit-learnRisk
Web security / User input
SQL injection and XSS testing in DVWA
Tested common web vulnerabilities in a controlled vulnerable application to understand how unsafe input handling becomes a platform risk.
- Observed SQL injection and XSS behavior in forms and browser-based workflows.
- Connected the findings to practical mitigations and safer input handling.
- Relevant to reporting modules, portals, assistance chatbots and public forms.
DVWASQLiXSS