中文
相关论文

相关论文: Containment Verification: AI Safety Guarantees Ind…

200 篇论文

Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…

密码学与安全 · 计算机科学 2026-02-12 Mohan Rajagopalan , Vinay Rao

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

人工智能 · 计算机科学 2025-09-30 Roham Koohestani

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…

密码学与安全 · 计算机科学 2025-03-04 Ishaan Domkundwar , Mukunda N S , Ishaan Bhola , Riddhik Kochhar

The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…

AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…

密码学与安全 · 计算机科学 2026-03-23 Ziling Zhou

Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…

密码学与安全 · 计算机科学 2026-03-04 Federico Villa , F. Betül Durak , Tadayoshi Kohno , Tapdig Maharramli , Franziska Roesner

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…

Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions and handle inputs…

密码学与安全 · 计算机科学 2026-01-16 Nadya Abaev , Denis Klimov , Gerard Levinov , David Mimran , Yuval Elovici , Asaf Shabtai

The rapid deployment of large language model (LLM)-based agents introduces a new class of risks, driven by their capacity for autonomous planning, multi-step tool integration, and emergent interactions. It raises some risk factors for…

多智能体系统 · 计算机科学 2025-12-04 Rafflesia Khan , Declan Joyce , Mansura Habiba

Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the system should retain strong offensive capability inside an…

密码学与安全 · 计算机科学 2026-05-04 Isaac David , Marco Guarnieri , Arthur Gervais

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving…

人工智能 · 计算机科学 2025-10-07 Beomjun Kim , Kangyeon Kim , Sunwoo Kim , Yeonsang Shin , Heejin Ahn

Verification and validation of agentic behavior have been suggested as important research priorities in efforts to reduce risks associated with the creation of general artificial intelligence (Russell et al 2015). In this paper we question…

人工智能 · 计算机科学 2016-10-12 David J. Jilk

The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf of users, every message crosses a trust boundary where the…

密码学与安全 · 计算机科学 2026-03-03 Sahar Abdelnabi , Amr Gomaa , Eugene Bagdasarian , Per Ola Kristensson , Reza Shokri

Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…

软件工程 · 计算机科学 2026-05-21 Youcheng Sun , Jiawen Liu , Daniel Kroening , Jason Xue

The rapid evolution of autonomous, agentic artificial intelligence within financial services has introduced an existential architectural crisis: large language models (LLMs) are probabilistic, non-deterministic systems operating in domains…

计算机科学中的逻辑 · 计算机科学 2026-04-03 Devakh Rashie , Veda Rashi

AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by…

人工智能 · 计算机科学 2026-05-27 Yige Li , Yunhao Feng , Jun Sun

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

密码学与安全 · 计算机科学 2026-05-08 Javad Forough , Marios Kogias , Hamed Haddadi

Data lakehouses run sensitive workloads, where AI-driven automation raises concerns about trust, correctness, and governance. We argue that API-first, programmable lakehouses provide the right abstractions for safe-by-design, agentic…

人工智能 · 计算机科学 2025-10-13 Jacopo Tagliabue , Ciro Greco

As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…

‹ 上一页 1 2 3 10 下一页 ›