Design Behaviour Codes (DBCs): A Taxonomy-Driven Layered Governance Benchmark for Large Language Models
G. Madan Mohan, Veena Kiran Nambiar, Kiranmayee Janardhan

TL;DR
This paper introduces the DBC benchmark, a structured governance layer for large language models that significantly reduces risk exposure through a taxonomy-driven, auditable control system evaluated across multiple domains and attack strategies.
Contribution
It presents the first empirical framework for a layered governance system (DBC) applied at inference time, improving risk mitigation and model safety in LLMs.
Findings
Risk exposure reduced by 36.8% with DBC layer
MDBC adherence scores improved from 8.6 to 8.7 out of 10
High agreement (Fleiss kappa > 0.70) in automated evaluation
Abstract
We introduce the Dynamic Behavioral Constraint (DBC) benchmark, the first empirical framework for evaluating the efficacy of a structured, 150-control behavioral governance layer, the MDBC (Madan DBC) system, applied at inference time to large language models (LLMs). Unlike training time alignment methods (RLHF, DPO) or post-hoc content moderation APIs, DBCs constitute a system prompt level governance layer that is model-agnostic, jurisdiction-mappable, and auditable. We evaluate the DBC Framework across a 30 domain risk taxonomy organized into six clusters (Hallucination and Calibration, Bias and Fairness, Malicious Use, Privacy and Data Protection, Robustness and Reliability, and Misalignment Agency) using an agentic red-team protocol with five adversarial attack strategies (Direct, Roleplay, Few-Shot, Hypothetical, Authority Spoof) across 3 model families. Our three-arm controlled…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Adversarial Robustness in Machine Learning · Computational and Text Analysis Methods
