The narration step in LLM-solver loops is vulnerable to prompt injection that inverts verified solver conclusions, and hardened prompts reduce but do not eliminate the risk under adaptive attacks.
hub
Enforceable Security Policies
4 Pith papers cite this work, alongside 1,266 external citations. Polarity classification is still indexing.
4
Pith papers citing it
1,266
external citations · external index
hub tools
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Presents a distributionally robust optimization method for sound probabilistic verification of Datalog policies in AI agents that bounds violation risk regardless of predicate correlations.
Introduces a layer-order automaton model that equates faithful online enforcement to regular prefix-closed languages under causal visibility and shows equivalence to deterministic edit automata while preserving layer-local invariants.
The paper presents a layered method to translate governance objectives from standards such as ISO/IEC 42001 into four control layers for agentic AI, with runtime guardrails limited to observable, determinate, and time-sensitive controls, shown via a procurement-agent case study.
citing papers explorer
-
Analyzing the Narration Gap in LLM-Solver Loops
The narration step in LLM-solver loops is vulnerable to prompt injection that inverts verified solver conclusions, and hardened prompts reduce but do not eliminate the risk under adaptive attacks.
-
Efficient and Sound Probabilistic Verification for AI Agents
Presents a distributionally robust optimization method for sound probabilistic verification of Datalog policies in AI agents that bounds violation risk regardless of predicate correlations.
-
Layer Order Semantics for Automata-Based Cybersecurity
Introduces a layer-order automaton model that equates faithful online enforcement to regular prefix-closed languages under causal visibility and shows equivalence to deterministic edit automata while preserving layer-local invariants.
-
From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI
The paper presents a layered method to translate governance objectives from standards such as ISO/IEC 42001 into four control layers for agentic AI, with runtime guardrails limited to observable, determinate, and time-sensitive controls, shown via a procurement-agent case study.