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

• URL: http://arxiv.org/abs/2606.13621v1
• Date: Thu, 11 Jun 2026 17:35:40 GMT
• Title: Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks
• Abstract summary: Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions.<n>We instantiate this through a constrained two-player safety game for network defense.<n>We derive topology-level metrics from the attractor structure and combine them with post-convergence behavior from shield-constrained adversarial multi-agent reinforcement learning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• HazardAuditor: From Executable Threats to Safer Computer-Use Agents [50.06351661912873]
  Existing guard models target static prompts and responses.<n>Existing safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn.<n>We introduce HazardAuditor, an execution-grounded framework that closes both gaps.
  arXiv  Detail & Related papers  (2026-09-14T07:09:33Z)
• AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent [53.82005364479556]
  Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities.<n>Existing safety mechanisms mainly rely on external guardrails.<n>We propose AgentLens, a white-box defense framework that performs runtime safety detection and representation-level mitigation.
  arXiv  Detail & Related papers  (2026-06-21T21:13:55Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy [51.758416625168]
  Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations.<n>We propose a framework for certification of complex, composed mechanisms.<n>We provide a principled and general framework for using composite mechanisms to certify robustness under complex threat models.
  arXiv  Detail & Related papers  (2026-05-20T22:17:29Z)
• Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis [18.33590637095743]
  Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time.<n>In black-box settings, defenders cannot modify model weights and must instead intervene at inference time.<n>This setting creates three practical challenges: harmful intent may be hidden by educational or role-play framing, deep safety analysis can introduce non-trivial latency, and long adversarial contexts can dilute the local cues that simpler filters rely on.<n>We propose Safety Context Injection (SCI), an inference-time framework that separates safety assessment from task generation and prepends a structured external risk report as injected safety context for the protected
  arXiv  Detail & Related papers  (2026-05-12T07:23:02Z)
• Detecting speculative leaks with compositional semantics [9.009704721347575]
  We propose a novel framework for detecting information flows introduced by speculative execution and reasoning about software defenses.<n>We develop Spectector, a symbolic analysis tool that uses our compositional framework and leverages SMT solvers to detect vulnerabilities and verify program security.
  arXiv  Detail & Related papers  (2026-03-31T14:32:12Z)
• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution [49.689452243966315]
  AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks.<n>We propose CausalArmor, a selective defense framework that computes lightweight, leave-one-out attributions at privileged decision points.<n> Experiments on AgentDojo and DoomArena demonstrate that CausalArmor matches the security of aggressive defenses.
  arXiv  Detail & Related papers  (2026-02-08T11:34:08Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• Countermind: A Multi-Layered Security Architecture for Large Language Models [0.0]
  This paper proposes Countermind, a multi-layered security architecture intended to shift defenses from a reactive, post hoc posture to a proactive, pre-inference, and intra-inference enforcement model.<n>The architecture proposes a fortified perimeter designed to structurally validate and transform all inputs, and an internal governance mechanism intended to constrain the model's semantic processing pathways before an output is generated.
  arXiv  Detail & Related papers  (2025-10-13T18:41:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.