Conference paper path
Security Evidence and CaseTrace
A security-evidence research direction that turns reviewer feedback into traceable public-source case evidence, uncertainty labels, and baseline comparison.
Thesis
Security papers become stronger when claims are mapped to reproducible case evidence, uncertainty, defense-control implications, and explicit comparison instead of broad threat narratives.
Why it matters now
AI/security research is often evaluated under scarce reviewer attention. Traceable evidence methods help reviewers see the technical contribution and its limits quickly.
Evidence surface
- WISA 2026 package reframed around a new contribution-first CaseTrace direction rather than a polished resubmission.
- Evidence package records 18 coded rows across 3 cases, source corpus, case index, missing-evidence notes, baseline comparison, and LNCS structure.
- CYBERSEC medical cybersecurity work translates FDA 524B, threat modeling, SBOM, Zero Trust, and Patch SLA into public teaching material.
Validation path
- Case corpus
- Uncertainty labels
- Baseline comparison
- Reviewer gates
Current outputs
CaseTrace manuscript path, readiness checklist, public talk material, and evidence mapping templates.
Scope control
The site only presents public-source methodology and teaching artifacts. Sensitive case material, controlled evidence, and unpublished details stay in their execution repos.
Questions
- What evidence makes a security case study reproducible enough for reviewer scrutiny?
- How can uncertainty labels prevent overclaiming in AI/security papers?
- What public teaching surface helps medical-AI teams operationalize cybersecurity controls?