Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks

Computer Science > Artificial Intelligence [Submitted on 11 Jun 2026] Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks Achraf Hsain, Sultan Almuhammadi Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions. We argue this is the wrong product. The same automata-theoretic machinery -- specification compilation, product game construction, attractor computation, and winning-region extraction -- is better read as a design-time analytical instrument whose outputs are structural insights about a system rather than runtime constraints on a deployed agent. We instantiate this through a constrained two-player safety game for network defense. The two specifications are enforced asymmetrically: the defender specification defines the unsafe region of the game, whereas the attacker specification restricts the adversary's legal actions during attractor computation. Solving the game yields a defensibility verdict -- a formal certificate that a topology-specification pair is or is not defensible -- with the associated winning region and shield. Beyond the binary verdict, we derive topology-level metrics from the attractor structure and combine them with post-convergence behavior from shield-constrained adversarial multi-agent reinforcement learning. Together these form a defensibility fingerprint capturing both a network's formal safety properties and its operational behavior under adaptive play. A what-if analysis shows that formal defensibility and operational effectiveness capture distinct aspects of security: small architectural changes can produce large shifts in operational outcomes while leaving formal safety margins nearly unchanged. Shield synthesis is thus most valuable not as a deployment mechanism for safe agents, but as a framework for answering architectural questions about whether, where, and how a system can be defended. The defensibility verdict is the output, not the safe policy. Comments: 26 pages, 7 figures, 7 tables. Under review at JAIR. Code: this https URL Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG); Multiagent Systems (cs.MA) Cite as: arXiv:2606.13621 [cs.AI]   (or arXiv:2606.13621v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.13621 Focus to learn more Submission history From: Achraf Hsain [view email] [v1] Thu, 11 Jun 2026 17:35:40 UTC (1,340 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CR cs.GT cs.LG cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)