The ADB Behavioural Taxonomy: A Black-Box Framework for Classifying Defensive and Deceptive Behavior in Large Language Models (Review Set v5.5)
Open access0 citations
Abstract
The ADB (AI Defensive Behaviour) Behavioural Taxonomy is a black-box framework for classifying how conversational large language models behave when they make errors or are challenged. This Reviewer's Set (v5.5, 87 pages) contains: 1. The ADB Story (26-page visual companion) 2. The Core Framework (15 behavioural codes, 4-gate discriminator, S1-S9 test protocol) 3. Redacted Evidence Excerpts (De-identified timestamps, prompts, and outputs for System 1, 2, and 3) LIMITATIONS: Provisional research instrument. No allegation of wrongdoing against any organisation is made or intended.
// Source
View paper (DOI)Open access versionOpenAlexZenodo (CERN European Organization for Nuclear Research)Published 2026-08-03
Authors: Imtiyaz Chanderki
Institutions: Solapur University