中文
相关论文

相关论文: VIPER-MCP: Detecting and Exploiting Taint-Style Vu…

200 篇论文

Multi-agent systems represent a significant advancement in artificial intelligence, enabling complex problem-solving through coordinated specialized agents. However, these systems face fundamental challenges in context management,…

多智能体系统 · 计算机科学 2025-05-01 Naveen Krishnan

Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and…

密码学与安全 · 计算机科学 2025-11-25 Strahinja Janjusevic , Anna Baron Garcia , Sohrob Kazerounian

Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large…

软件工程 · 计算机科学 2025-05-22 Yuxuan Wang , Jingshu Chen , Qingyang Wang

The Model Context Protocol (MCP) is increasingly adopted to standardize the interaction between LLM agents and external tools. However, this trend introduces a new threat: Tool Poisoning Attacks (TPA), where tool metadata is poisoned to…

密码学与安全 · 计算机科学 2026-01-16 Zhiqiang Wang , Haohua Du , Guanquan Shi , Junyang Zhang , HaoRan Cheng , Yunhao Yao , Kaiwen Guo , Xiang-Yang Li

Developers usually use TPLs to facilitate the development of the projects to avoid reinventing the wheels, however, the vulnerable TPLs indeed cause severe security threats. The majority of existing research only considered whether projects…

软件工程 · 计算机科学 2024-09-05 Fangyuan Zhang , Lingling Fan , Sen Chen , Miaoying Cai , Sihan Xu , Lida Zhao

AI agent protocols -- including MCP, A2A, ANP, and ACP -- enable autonomous agents to discover capabilities, delegate tasks, and compose services across trust boundaries. Despite massive deployment (MCP alone has 97M+ monthly SDK…

密码学与安全 · 计算机科学 2026-03-26 Shenghan Zheng , Qifan Zhang

Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox (TVP): increasing…

密码学与安全 · 计算机科学 2025-10-22 Zijie Xu , Minfeng Qi , Shiqing Wu , Lefeng Zhang , Qiwen Wei , Han He , Ningran Li

While the automated detection of cryptographic API misuses has progressed significantly, its precision diminishes for intricate targets due to the reliance on manually defined patterns. Large Language Models (LLMs) offer a promising…

密码学与安全 · 计算机科学 2026-03-19 Yifan Xia , Zichen Xie , Peiyu Liu , Kangjie Lu , Yan Liu , Wenhai Wang , Shouling Ji

Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. However, existing retrieval methods typically match queries…

计算与语言 · 计算机科学 2025-11-05 Elias Lumer , Faheem Nizar , Anmol Gulati , Pradeep Honaganahalli Basavaraju , Vamse Kumar Subbiah

We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning,…

人工智能 · 计算机科学 2026-02-05 Yang Zhou , Mingyu Zhao , Zhenting Wang , Difei Gu , Bangwei Guo , Ruosong Ye , Ligong Han , Can Jin , Dimitris N. Metaxas

Recent agentic-robotics systems, from Code-asPolicies to modern vision-language-action (VLA) foundation models, presuppose that drivers, SDKs, or ROS-style primitives for the target hardware already exist. Writing those primitives is the…

机器人学 · 计算机科学 2026-05-12 Quilee Simeon , Justin M. Wei , Yile Fan

Software vulnerabilities present a persistent security challenge, with over 25,000 new vulnerabilities reported in the Common Vulnerabilities and Exposures (CVE) database in 2024 alone. While deep learning based approaches show promise for…

密码学与安全 · 计算机科学 2025-07-23 Ahmed Lekssays , Hamza Mouhcine , Khang Tran , Ting Yu , Issa Khalil

AI agents, autonomous digital actors, need agent-native protocols; existing methods include GUI automation and MCP-based skills, with defects of high token consumption, fragmented interaction, inadequate security, due to lacking a unified…

人工智能 · 计算机科学 2026-04-07 Xu Mingze

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

密码学与安全 · 计算机科学 2025-02-14 Karl Tamberg , Hayretdin Bahsi

The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-structured, and unstructured data. While Large Language Models…

数据库 · 计算机科学 2025-05-19 Chao Zhang , Shaolei Zhang , Quehuan Liu , Sibei Chen , Tong Li , Ju Fan

Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…

密码学与安全 · 计算机科学 2025-11-06 Geoff McDonald , Jonathan Bar Or

MCP standardizes how LLMs interact with external systems, forming the foundation for general agents. However, existing MCP benchmarks remain narrow in scope: they focus on read-heavy tasks or tasks with limited interaction depth, and fail…

Prompt tuning represents a valuable technique for adapting pre-trained visual-language models (VLM) to various downstream tasks. Recent advancements in CoOp-based methods propose a set of learnable domain-shared or image-conditional textual…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Hantao Yao , Rui Zhang , Changsheng Xu

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

密码学与安全 · 计算机科学 2023-05-08 Kai Greshake , Sahar Abdelnabi , Shailesh Mishra , Christoph Endres , Thorsten Holz , Mario Fritz

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

人工智能 · 计算机科学 2026-02-20 Arnold Cartagena , Ariane Teixeira
‹ 上一页 1 8 9 10 下一页 ›