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…

This survey analyzes the unique security threats posed by complex, multi-agent AI systems and proposes Confidential Computing (CC) using Trusted Execution Environments (TEEs) as a hardware-rooted defe…

The paper proposes and validates a comprehensive four-layer Zero Trust security architecture designed to mitigate critical vulnerabilities in autonomous AI agents handling Protected Health Information…

The paper proposes the Redpanda Agentic Data Plane (ADP), an architecture that uses out-of-band metadata channels to deterministically enforce security policies and governance for autonomous AI agents…

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…

AgenTEE is a system that enables the secure, confidential execution of complex LLM agent pipelines directly on edge devices by using isolated confidential virtual machines.

The paper reports on penetration tests conducted on proprietary, large-scale AI agent systems, finding that security vulnerabilities persist despite stricter development standards.

This paper systematically analyzes security risks in cloud-hosted, tool-enabled AI agents, concluding that most risks stem from over-privileged tools and capability-intent mismatches rather than novel…

AgentTrust is a novel runtime safety layer that intercepts and evaluates AI agent tool calls before execution, achieving high accuracy in detecting unsafe actions across complex and obfuscated scenari…

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

The paper introduces MolTrust, a production-deployed trust infrastructure built on W3C standards (VCs and DIDs) that provides a verifiable, multi-layered authorization framework for autonomous AI agen…

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 proposes AgentDID, a decentralized framework using DIDs and verifiable credentials to provide trustless identity authentication and dynamic state verification for autonomous, self-managed AI…

This paper reviews recent EU AI regulatory documents to clarify definitions and synthesize current provisions regarding security, privacy, and autonomous agentic AI.

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…

KYA introduces a framework-agnostic trust and governance layer for autonomous systems that ensures actions are authorized, policy-conforming, and verifiable through a combination of novel primitives.

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to…

This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.

The paper argues that the Authorization-Execution Gap (AEG)—the divergence between intended authorization and actual execution—is a critical safety and security flaw in open-world agents, requiring so…

This paper analyzes the security, privacy, and ethical risks associated with OpenClaw, a locally executable AI agent system, concluding that these risks pose major barriers to its trustworthy deployme…