Alignment contracts define scope, allowed effects, budgets and disclosure rules as safety properties over finite effect traces, with decidable admissibility, refinement rules, and Lean-verified soundness under an observability assumption.
Computer29(2), 38–47 (1996)
7 Pith papers cite this work, alongside 5,820 external citations. Polarity classification is still indexing.
7
Pith papers citing it
5,820
external citations · OpenAlex
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
The paper develops semiring-annotated topological spaces (seats) extending epistemic logic to model resource costs for observing evidence, with sound and strongly complete axiomatizations for resource-indexed modalities.
SecureMCP integrates RBAC with five sequential defense modules in an MCP server to achieve 82.3% policy compliance against adversarial LLM SQL queries in AIoT while preserving execution accuracy.
A prototype framework collects legal requirements and translates them into machine-actionable policies for federated data processing networks via policy-as-code and LLMs.
Frontier AI agents introduce new confidentiality, integrity, and availability risks through changed assumptions on code-data separation and authority boundaries, requiring layered defenses like sandboxing and policy enforcement.
citing papers explorer
-
Alignment Contracts for Agentic Security Systems
Alignment contracts define scope, allowed effects, budgets and disclosure rules as safety properties over finite effect traces, with decidable admissibility, refinement rules, and Lean-verified soundness under an observability assumption.
-
Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
-
Knowledge on a Budget
The paper develops semiring-annotated topological spaces (seats) extending epistemic logic to model resource costs for observing evidence, with sound and strongly complete axiomatizations for resource-indexed modalities.
-
SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems via Model Context Protocol
SecureMCP integrates RBAC with five sequential defense modules in an MCP server to achieve 82.3% policy compliance against adversarial LLM SQL queries in AIoT while preserving execution accuracy.
-
Compliance Management for Federated Data Processing
A prototype framework collects legal requirements and translates them into machine-actionable policies for federated data processing networks via policy-as-code and LLMs.
-
Security Considerations for Artificial Intelligence Agents
Frontier AI agents introduce new confidentiality, integrity, and availability risks through changed assumptions on code-data separation and authority boundaries, requiring layered defenses like sandboxing and policy enforcement.
- Reflections on the design, applications and implementations of the normative specification language eFLINT