中文
相关论文

相关论文: Structural Enforcement of Goal Integrity in AI Age…

200 篇论文

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…

人工智能 · 计算机科学 2026-05-29 Benlong Wu , Weiming Zhang , Kejiang Chen , Han Fang , Nenghai Yu

Large Language Model (LLM)-based agents are increasingly adopted in high-stakes settings, but current benchmarks evaluate mainly whether a task was completed, not how. We introduce Procedure-Aware Evaluation (PAE), a framework that…

人工智能 · 计算机科学 2026-03-04 Hongliu Cao , Ilias Driouich , Eoin Thomas

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

Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…

人工智能 · 计算机科学 2026-01-26 Zhibo Liang , Tianze Hu , Zaiye Chen , Mingjie Tang

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…

密码学与安全 · 计算机科学 2026-03-19 Saikat Maiti

Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…

多智能体系统 · 计算机科学 2026-04-28 Juan A. Wibowo , George C. Polyzos

This paper investigates an emergent alignment phenomenon in frontier large language models termed peer-preservation: the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model…

人工智能 · 计算机科学 2026-04-10 Juergen Dietrich

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…

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

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…

密码学与安全 · 计算机科学 2026-02-11 Manish Bhattarai , Minh Vu

Artificial intelligence (AI) agents are increasingly capable of initiating financial transactions on behalf of users or other agents. This evolution introduces a fundamental challenge: verifying both the authenticity of an autonomous agent…

密码学与安全 · 计算机科学 2025-11-21 Vivek Acharya

Contemporary AI governance frameworks rely heavily on post hoc oversight, policy guidance, and behavioral alignment techniques, yet these mechanisms become fragile as systems gain autonomy, speed, and operational opacity. This paper…

密码学与安全 · 计算机科学 2026-03-19 Adam Massimo Mazzocchetti

The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…

人工智能 · 计算机科学 2026-03-02 Sheng Cao , Zhao Chang , Chang Li , Hannan Li , Liyao Fu , Ji Tang

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…

人工智能 · 计算机科学 2026-02-17 William Waites

The ongoing shift of AI models from centralized cloud APIs to local AI agents on edge devices is enabling \textit{Client-Side Autonomous Agents (CSAAs)} -- persistent personal agents that can plan, access local context, and invoke tools on…

网络与互联网体系结构 · 计算机科学 2026-03-05 Taotao Wang , Lizhao You , Jingwen Tong , Chonghe Zhao , Shengli Zhang

The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially high-risk scenarios. Despite advances in safety alignment techniques, current models remain…

人工智能 · 计算机科学 2026-05-05 Jiajia Li , Xiaoyu Wen , Zhongtian Ma , Shuyue Hu , Qiaosheng Zhang , Zhen Wang

AI memory systems are evolving toward unified context layers that enable efficient cross-agent collaboration and multi-tool workflows, facilitating better accumulation of personal data and learning of user preferences. However,…

密码学与安全 · 计算机科学 2026-01-13 Xing Zhou , Dmitrii Ustiugov , Haoxin Shang , Kisson Lin

As AI systems evolve into distributed ecosystems with autonomous execution, asynchronous reasoning, and multi-agent coordination, the absence of scalable, decoupled governance poses a structural risk. Existing oversight mechanisms are…

机器学习 · 计算机科学 2025-08-28 Suyash Gaurav , Jukka Heikkonen , Jatin Chaudhary

Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these systems to catastrophic risks, ranging from unintentional…

人工智能 · 计算机科学 2026-04-06 Yang Li , Yule Liu , Xinlei He , Youjian Zhao , Qi Li , Ke Xu
‹ 上一页 1 2 3 10 下一页 ›