Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction
cs.AI, cs.CR, cs.GT, cs.LG, cs.MA
Submitted: 2026-06-11
Updated: 2026-09-15
Comments: 36 pages, 8 figures, 7 tables. Code: https://github.com/AchrafHsain7/Bastion Shielded analysis; system defensibility; safety games; shield synthesis; adversarial multi-agent reinforcement learning; network security
Code: https://github.com/AchrafHsain7/Bastion
License: http://creativecommons.org/licenses/by/4.0/
The gist: Formal safety analysis determines whether a system admits a safe defense; adaptive evaluation characterizes the operating quality sustained under adversarial interaction.
Terminology
Abstract
Formal safety analysis determines whether a system admits a safe defense; adaptive evaluation characterizes the operating quality sustained under adversarial interaction. Both answers matter because systems with the same safety verdict can impose very different operational burdens. We introduce shielded analysis, a design-time framework that derives these answers from one encoded system while keeping the safety requirement and admissible threat model independently variable. It returns a defensibility certificate and a four-axis defensibility fingerprint spanning structural margin, shield latitude, and adaptive operating quality. Each axis is informative in its own right; their relationships show whether formal and operational assessments agree, diverge, or respond differently to system changes. We instantiate the framework for network defense on a reference segment and four controlled perturbations spanning topology, safety requirements, and adversary capabilities. Every configuration is certified defensible, yet two topology variants with nearly identical structural profiles sustain mean clean-host fractions of 22.7% and 80.7% under adaptive pressure. Shielded analysis turns a safety-game solution into a comparative instrument: it determines whether a defense exists, characterizes what that defense requires, and identifies which system changes strengthen it.
Sources
- Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning
- CybORG: A Gym for the Development of Autonomous Cyber Agents
- Dynamic Adversarial Resource Allocation: the dDAB Game
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection