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 proposes a methodology for auditable trustworthiness levels in AI governance with a formal framework and a lightweight procedure.

This paper systematizes the security challenges of open agentic systems, concluding that while attack characterization is mature, the field lacks robust guidelines for operational governance, memory i…

The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.

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 Semantic Gateway and a Zero-Trust security model to formally validate and secure autonomous AI agents operating in enterprise systems, achieving a 100% discovery rate of unauthori…

This paper systematically maps the expanded attack surface of agentic AI systems, identifying new threat vectors like RAG poisoning and cross-agent manipulation, and proposes a comprehensive security…

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 introduces CAGE-1, an evaluation framework for deciding the readiness of enterprise agents for deployment, focusing on control, assurance, and governance.

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

The paper defines AI Identity as the correspondence between an agent's declared state and its observed behavior, concluding that current infrastructure and standards are fundamentally inadequate for g…

The paper argues that Agentic AI fundamentally breaks the historical security tradeoff between deception fidelity and scale, necessitating a shift from authenticating actors to evaluating actions.

The paper proposes a tool-mediated LLM architecture for autonomous cyber defense, formally proving its stability and demonstrating that it significantly reduces an attacker's expected payoff in real-w…

The paper proposes a management framework, using a governed AI query-broker artifact, to safely integrate generative AI into high-risk operational decision support, such as Security Operations Centers…

The paper analyzes the failure modes of current AI containment methods when the agent itself is the adversary, deriving five necessary architectural requirements for durable safety.

This paper empirically demonstrates that the architectural design of multi-agent systems significantly impacts their security, finding that coordination mechanisms can introduce vulnerabilities greate…

The paper introduces ACIArena, a unified and comprehensive evaluation framework designed to systematically test the robustness of Multi-Agent Systems against complex Agent Cascading Injection attacks.

The paper introduces POIROT, a novel protocol that uses the agents within a multi-agent system itself to diagnose and detect failures, demonstrating superior performance over traditional evaluation me…