English
Related papers

Related papers: DynaTrust: Defending Multi-Agent Systems Against S…

200 papers

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

Rapid transitions are important for quick response of consensus-based, multi-agent networks to external stimuli. While high-gain can increase response speed, potential instability tends to limit the maximum possible gain, and therefore,…

Systems and Control · Electrical Eng. & Systems 2021-08-10 Anuj Tiwari , Santosh Devasia

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware…

Artificial Intelligence · Computer Science 2026-01-28 Shanyv Liu , Xuyang Yuan , Tao Chen , Zijun Zhan , Zhu Han , Danyang Zheng , Weishan Zhang , Shaohua Cao

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…

Machine Learning · Computer Science 2026-05-25 Jonathan Nöther , Adish Singla , Goran Radanovic

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…

Machine Learning · Computer Science 2025-02-06 Chen Henry Wu , Rishi Shah , Jing Yu Koh , Ruslan Salakhutdinov , Daniel Fried , Aditi Raghunathan

As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities. However, backdoor attacks are typically…

Cryptography and Security · Computer Science 2025-10-14 Pengyu Zhu , Zhenhong Zhou , Yuanhe Zhang , Shilinlu Yan , Kun Wang , Sen Su

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…

Cryptography and Security · Computer Science 2025-10-14 Pengyu Zhu , Lijun Li , Yaxing Lyu , Li Sun , Sen Su , Jing Shao

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Artificial Intelligence · Computer Science 2025-09-25 Huizhen Shu , Xuying Li , Zhuo Li

The rise of advanced persistent threats (APTs) has marked a significant cybersecurity challenge, characterized by sophisticated orchestration, stealthy execution, extended persistence, and targeting valuable assets across diverse sectors.…

Cryptography and Security · Computer Science 2024-04-19 Yuntao Wang , Han Liu , Zhendong Li , Zhou Su , Jiliang Li

Large Language Model (LLM)-based Multi-agent Systems (MAS) have demonstrated remarkable capabilities in various complex tasks, ranging from collaborative problem-solving to autonomous decision-making. However, as these systems become…

Cryptography and Security · Computer Science 2025-02-18 Shilong Wang , Guibin Zhang , Miao Yu , Guancheng Wan , Fanci Meng , Chongye Guo , Kun Wang , Yang Wang

Deep neural networks (DNNs) have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that DNNs are vulnerable to…

Cryptography and Security · Computer Science 2022-10-07 Lichao Sun , Yingtong Dou , Carl Yang , Ji Wang , Yixin Liu , Philip S. Yu , Lifang He , Bo Li

Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic, real-time, multi-agent scenarios, such as collaborative…

Multiagent Systems · Computer Science 2026-01-01 Shaurya Mallampati , Rashed Shelim , Walid Saad , Naren Ramakrishnan

In this paper, we explore the robustness of the Multi-Task Deep Neural Networks (MT-DNN) against non-targeted adversarial attacks across Natural Language Understanding (NLU) tasks as well as some possible ways to defend against them. Liu et…

Computation and Language · Computer Science 2020-01-16 Kashyap Coimbatore Murali

Deep neural networks have been shown to suffer from critical vulnerabilities under adversarial attacks. This phenomenon stimulated the creation of different attack and defense strategies similar to those adopted in cyberspace security. The…

Cryptography and Security · Computer Science 2021-05-07 Ruoxi Qin , Linyuan Wang , Xingyuan Chen , Xuehui Du , Bin Yan

Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration capabilities. As these systems become more complex and…

Software Engineering · Computer Science 2026-03-24 Lingzhe Zhang , Tong Jia , Mingyu Wang , Weijie Hong , Chiming Duan , Minghua He , Rongqian Wang , Xi Peng , Meiling Wang , Gong Zhang , Renhai Chen , Ying Li

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…

Machine Learning · Computer Science 2021-02-24 Ngoc Duy Nguyen , Thanh Thi Nguyen , Doug Creighton , Saeid Nahavandi

Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial…

Multiagent Systems · Computer Science 2023-12-20 Lebin Yu , Yunbo Qiu , Quanming Yao , Yuan Shen , Xudong Zhang , Jian Wang

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs…

Machine Learning · Computer Science 2020-12-15 Wei Jin , Yaxin Li , Han Xu , Yiqi Wang , Shuiwang Ji , Charu Aggarwal , Jiliang Tang

In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing adversarial studies on MAS target only shallow tasks and do not consider adaptive…

Computation and Language · Computer Science 2026-05-15 Alexandre Le Mercier , Chris Develder , Thomas Demeester

Deep Q-Network (DQN) based multi-agent systems (MAS) for reinforcement learning (RL) use various schemes where in the agents have to learn and communicate. The learning is however specific to each agent and communication may be…

Machine Learning · Computer Science 2020-08-11 Abdul Mueed Hafiz , Ghulam Mohiuddin Bhat