Skip to main content
RaoufResearchOS
English
Sydney, AustraliaCurrent Sydney Time—
Press Escape to close this window.
Write-ups

Papers and write-ups

Write-ups

Technical analysis, CTF solutions, and engineering logs.

Write-ups

Results: 7

Attesting What an AI Agent Was Allowed to Do

Signed, offline-verifiable evidence of an agent's actions after a guardrail miss: 138/138 classifier-missed cases contained, 9/140 to 0/140 on AgentDojo.

Research Papers

Papers: 5

Original titles and PDFs are in English.

Banking Shield: Machine-Checked Absence Claims for Privacy-Sensitive AI Explanations

Fictional, non-bank research prototype that turns privacy and overclaim boundaries into machine-checkable evidence: a 46-name forbidden-field firewall whose rejections become audit events, a deterministic offline AI privacy firewall, and per-response privacy receipts anchored in per-session HMAC audit chains. At the evidence freeze all 417/417 unit tests, 43/43 end-to-end checks, and 27/27 security checks passed across three privacy audits and a no-egress static gate, with a formative five-tester dry run (30 sessions) recording zero sensitive values in evidence and 5/5 non-claim checklist comprehension.

(opens in a new tab)

Search

Find a project, paper, write-up, or page.

30 / 41 · Search results

↑ ↓ Workspace NavigationEnter OpenEsc Close