
Rubrics-as-an-Attack-Surface
Research code for Rubric-Induced Preference Drift (RIPD): evolutionary rubric search, benchmark-preserving selection, and DPO policy misalignment…
adversarial-attackai-securityeducation+2
7

Research code for Rubric-Induced Preference Drift (RIPD): evolutionary rubric search, benchmark-preserving selection, and DPO policy misalignment…

An AI-powered Personal Identifiable Information (PII) scanner.

Research implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.

MCP server for Google search and page fetching using headless Chromium