中文
相关论文

相关论文: Who's the Mole? Modeling and Detecting Intention-H…

200 篇论文

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

密码学与安全 · 计算机科学 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal electronic health records data, medical images, radiology reports, and clinical notes.…

人工智能 · 计算机科学 2026-05-12 Baraa Al Jorf , Farah E. Shamout

Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness critical. A significant and underexplored risk is intentional deception, where an LLM deliberately fabricates…

机器学习 · 计算机科学 2026-05-04 Zhaomin Wu , Mingzhe Du , See-Kiong Ng , Bingsheng He

Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation,…

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…

密码学与安全 · 计算机科学 2026-05-12 Ziwen Cai , Yihe Zhang , Xiali Hei

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

密码学与安全 · 计算机科学 2025-06-02 Hanrong Zhang , Jingyuan Huang , Kai Mei , Yifei Yao , Zhenting Wang , Chenlu Zhan , Hongwei Wang , Yongfeng Zhang

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

密码学与安全 · 计算机科学 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

Large Language Models (LLMs) are increasingly explored for legal argument generation, yet they pose significant risks of manipulation through hallucination and ungrounded persuasion, and often fail to utilize provided factual bases…

人工智能 · 计算机科学 2025-10-27 Li Zhang , Kevin D. Ashley

Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable…

密码学与安全 · 计算机科学 2025-02-06 Nan Wang , Kane Walter , Yansong Gao , Alsharif Abuadbba

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

计算与语言 · 计算机科学 2026-04-14 Hwan Chang , Yonghyun Jun , Hwanhee Lee

LLM-based multi-agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual agents fail or behave adversarially. In this work, we study the automated design of agentic systems…

机器学习 · 计算机科学 2026-05-25 Jonathan Nöther , Adish Singla , Goran Radanovic

Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…

机器学习 · 计算机科学 2025-10-08 Jonathan Nöther , Adish Singla , Goran Radanovic

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

密码学与安全 · 计算机科学 2024-06-18 Stephen Burabari Tete

With the recent emergence of revolutionary autonomous agentic systems, research community is witnessing a significant shift from traditional static, passive, and domain-specific AI agents toward more dynamic, proactive, and generalizable…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Huanjin Yao , Ruifei Zhang , Jiaxing Huang , Jingyi Zhang , Yibo Wang , Bo Fang , Ruolin Zhu , Yongcheng Jing , Shunyu Liu , Guanbin Li , Dacheng Tao

Modeling multi-agent systems requires understanding how agents interact. Such systems are often difficult to model because they can involve a variety of types of interactions that layer together to drive rich social behavioral dynamics.…

机器学习 · 计算机科学 2023-01-26 Fan-Yun Sun , Isaac Kauvar , Ruohan Zhang , Jiachen Li , Mykel Kochenderfer , Jiajun Wu , Nick Haber

Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process…

密码学与安全 · 计算机科学 2024-12-24 Feiran Jia , Tong Wu , Xin Qin , Anna Squicciarini

The final frontier for simulation is the accurate representation of complex, real-world social systems. While agent-based modeling (ABM) seeks to study the behavior and interactions of agents within a larger system, it is unable to…

人工智能 · 计算机科学 2023-08-16 Edward Junprung

Recent advancements in Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks. However, current research largely relies on manual, task-specific design, limiting their…

计算与语言 · 计算机科学 2025-02-28 Yu Shang , Yu Li , Keyu Zhao , Likai Ma , Jiahe Liu , Fengli Xu , Yong Li

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful…

人工智能 · 计算机科学 2026-05-28 Yongxiang Li , Moxin Li , Zhixin Ma , Fengbin Zhu , Dongrui Liu , Wenjie Wang , Fuli Feng