English
Related papers

Related papers: Agent Tools Orchestration Leaks More: Dataset, Ben…

200 papers

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…

Cryptography and Security · Computer Science 2026-05-15 Surada Suwansathit , Yuxuan Zhang , Guofei Gu

Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of…

Artificial Intelligence · Computer Science 2025-03-25 Samuel Schmidgall , Michael Moor

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume that task-appropriate tools are reliable within their intended scope. This assumption is…

Artificial Intelligence · Computer Science 2026-05-27 Yunhui Gan , Tan Pan , Kaiyu Guo , Limei Han , Weimiao Yu , Guangnan Ye , Chen Jiang , Yuan Cheng

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…

Cryptography and Security · Computer Science 2026-04-23 Hanzhi Liu , Chaofan Shou , Xiaonan Liu , Hongbo Wen , Yanju Chen , Ryan Jingyang Fang , Yu Feng

Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…

Information Theory · Computer Science 2021-04-19 Sara Saeidian , Giulia Cervia , Tobias J. Oechtering , Mikael Skoglund

The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…

Artificial Intelligence · Computer Science 2025-11-13 Niclas Flehmig , Mary Ann Lundteigen , Shen Yin

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Cryptography and Security · Computer Science 2025-09-10 Hongfei Xia , Hongru Wang , Zeming Liu , Qian Yu , Yuhang Guo , Haifeng Wang

In this study, we introduce the concept of OKR-Agent designed to enhance the capabilities of Large Language Models (LLMs) in task-solving. Our approach utilizes both self-collaboration and self-correction mechanism, facilitated by…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Yi Zheng , Chongyang Ma , Kanle Shi , Haibin Huang

Communication topology is a critical factor in the utility and safety of LLM-based multi-agent systems (LLM-MAS), making it a high-value intellectual property (IP) whose confidentiality remains insufficiently studied. Existing topology…

Cryptography and Security · Computer Science 2026-03-20 Zixun Xiong , Gaoyi Wu , Lingfeng Yao , Miao Pan , Xiaojiang Du , Hao Wang

As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework…

Multiagent Systems · Computer Science 2026-05-12 Yang Shen , Zhenyi Yi , Ziyi Zhao , Lijun Sun , Dongyang Li , Chin-Teng Lin , Yuhui Shi

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Artificial Intelligence · Computer Science 2026-03-13 Yonas Atinafu , Robin Cohen

Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications. Yet an overlooked threat is Reasoning-Level…

Machine Learning · Computer Science 2026-05-12 Xinyu Li , Ronghui Mu , Lin Li , Tianjin Huang , Gaojie Jin

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of…

Artificial Intelligence · Computer Science 2026-04-15 Yongxuan Wu , Xixun Lin , He Zhang , Nan Sun , Kun Wang , Chuan Zhou , Shirui Pan , Yanan Cao

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Machine Learning · Computer Science 2022-09-14 Jiayuan Ye , Aadyaa Maddi , Sasi Kumar Murakonda , Vincent Bindschaedler , Reza Shokri

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and…

Computation and Language · Computer Science 2026-05-28 Maike Züfle , Jan Niehues

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…

Machine Learning · Computer Science 2025-10-10 Jiashu Tao , Reza Shokri

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

Computation and Language · Computer Science 2026-03-04 Aradhye Agarwal , Gurdit Siyan , Yash Pandya , Joykirat Singh , Akshay Nambi , Ahmed Awadallah

Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Existing approaches tightly couple tool execution with…

Artificial Intelligence · Computer Science 2026-03-02 Tao Zhe , Haoyu Wang , Bo Luo , Min Wu , Wei Fan , Xiao Luo , Zijun Yao , Haifeng Chen , Dongjie Wang

Large language models are powerful generalists, yet solving deep and complex problems such as those of the Humanity's Last Exam (HLE) remains both conceptually challenging and computationally expensive. We show that small orchestrators…