The paper introduces MuSimA, a web-based tool that addresses the lack of large-scale synthetic dataset generation for Attribute-based Access Control (ABAC) systems.

This paper introduces EXTree, a novel structure for Attribute-based Access Control (ABAC) policies that optimizes for both fast evaluation and human-understandable explanations when access is denied.

The paper proposes an architectural proxy (MCP) to enforce robust, reliable tool access control for LLM agents, demonstrating that this structural enforcement is necessary because prompt-based restric…

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

Permit is a novel framework that enforces fine-grained, permission-aware control over the hidden states of LLMs, preventing information leakage even when sensitive data is present in the context.

The paper proposes a novel design for website interaction that provides fine-grained access control, enabling agentic AI to safely perform delegated critical tasks on a user's behalf.

The paper proposes a compositional governance framework to provide richer, dynamic authorization semantics necessary for governing autonomous agentic AI systems, moving beyond traditional static IAM m…

The paper proposes a vision for system-level defenses against indirect prompt injection attacks targeting AI agents, emphasizing structured control and human oversight.

The paper introduces a new benchmark and decomposition method, Sufficiency-Tightness Decomposition, demonstrating that current coding agents struggle to accurately infer least-privilege authorization,…

This paper provides the first comprehensive security analysis of the Agent Skills framework, identifying severe structural vulnerabilities that require fundamental architectural changes rather than si…

The paper proposes a structured prompt engineering framework to enhance the integrity and reliability of Chain-of-Thought (CoT) reasoning in LLMs, demonstrating significant improvements in security-se…

This paper introduces UPAttack, a novel threat model demonstrating that focusing on explicit usability requirements can cause LLMs to generate insecure code by neglecting implicit security constraints…

The paper introduces a validated, consensus-labeled prompt bank that separates requests for executable malicious code (weapons) from requests for general harmful security knowledge, providing a more g…

AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.

The paper investigates how users perceive and utilize security and privacy transparency in consumer-facing generative AI, finding that users rely on proxies like popularity and require actionable, tru…

The paper introduces Conleash, a client-side middleware that uses a risk lattice to enforce granular, boundary-scoped authorization for tool invocations, significantly improving user consent and secur…

The paper introduces the Open Agent Passport (OAP), a deterministic pre-action authorization framework that intercepts and validates AI agent tool calls against a declarative policy, achieving a 0% su…

The paper introduces CAESAR, a novel multi-agent framework that coordinates LLM agents across five specialized roles to improve success rates and stability in complex, multi-stage cyber intrusion task…

The paper introduces AC4A, an access control framework that allows users to precisely limit the capabilities of LLM agents, ensuring they only access the specific APIs or parts of web pages necessary…