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 systematizes the interaction between autonomous AI agents and blockchain platforms using a bidirectional trust framework, identifying significant gaps in current standards and proposing a ta…

The paper introduces the Agent Name Service (ANS), a DNS-inspired trust layer implemented in Kubernetes, to provide secure discovery, identity, and governance for autonomous AI agents.

The paper introduces GAAP, an execution environment that deterministically guarantees the confidentiality of private user data by enforcing user-defined permission specifications on AI agents, even ag…

The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…

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…

AgentWall is a runtime safety layer that intercepts and evaluates all proposed actions from local AI agents against a declarative policy, ensuring safety before execution.

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…

This paper conducts the first real-world safety evaluation of the personal AI agent OpenClaw, demonstrating that its broad system access creates inherent vulnerabilities that significantly increase th…

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 introduces a comprehensive security framework, AgentRFC, to systematically analyze and test the security conformance of various AI agent protocols, identifying critical design gaps, especial…

This paper analyzes 470 security advisories in the OpenClaw AI agent framework, demonstrating that the system's structural weakness lies in per-layer trust enforcement, enabling cross-layer remote cod…

The paper introduces AIP, a novel protocol using Invocation-Bound Capability Tokens (IBCTs) to provide verifiable identity and secure delegation across Model Context Protocol (MCP) and Agent-to-Agent…

The paper introduces AgentWard, a lifecycle-oriented, defense-in-depth architecture designed to systematically secure autonomous AI agents by protecting them across all stages of their operation.

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 introduces Parallax, an architectural framework that structurally separates AI reasoning from action execution to ensure robust safety for autonomous agents, achieving high attack mitigation…

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

This paper provides a systematic, layered review of security risks and defense strategies for autonomous agent frameworks, using OpenClaw as a case study to address the current lack of integrated rese…

ClawLess introduces a formally verified security framework that enforces fine-grained policies on autonomous AI agents, mitigating risks associated with their ability to run code and retrieve informat…