English
Related papers

Related papers: GAMBIT: A Three-Mode Benchmark for Adversarial Rob…

200 papers

The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised…

Artificial Intelligence · Computer Science 2026-04-28 Rui Miao , Yixin Liu , Yili Wang , Xu Shen , Yue Tan , Yiwei Dai , Shirui Pan , Xin Wang

In adversarial multi-armed bandits, two performance measures are commonly used: static regret, which compares the learner to the best fixed arm, and dynamic regret, which compares it to the best sequence of arms. While optimal algorithms…

Machine Learning · Computer Science 2026-02-18 Jian Qian , Chen-Yu Wei

Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Gaurang Sriramanan , Sravanti Addepalli , Arya Baburaj , R. Venkatesh Babu

Agentic artificial intelligence (AI) -- multi-agent systems that combine large language models with external tools and autonomous planning -- are rapidly transitioning from research laboratories into high-stakes domains. Our earlier "Basic"…

Artificial Intelligence · Computer Science 2025-09-16 Manish Shukla

Detection of adversarial examples has been a hot topic in the last years due to its importance for safely deploying machine learning algorithms in critical applications. However, the detection methods are generally validated by assuming a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Federica Granese , Marine Picot , Marco Romanelli , Francisco Messina , Pablo Piantanida

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…

Machine Learning · Computer Science 2025-10-08 Jonathan Nöther , Adish Singla , Goran Radanovic

The rapid integration of Large Language Models (LLMs) into Multi-Agent Systems (MAS) has significantly enhanced their collaborative problem-solving capabilities, but it has also expanded their attack surfaces, exposing them to…

Cryptography and Security · Computer Science 2026-04-29 Pablo Mateo-Torrejón , Alfonso Sánchez-Macián

Current schemes to detect cheating in online games often build on the assumption that the applied cheat takes actions that are drastically different from normal behavior. For instance, an Aimbot for a first-person shooter is used by an…

Cryptography and Security · Computer Science 2020-04-28 Tim Witschel , Christian Wressnegger

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Fudong Lin , Jiadong Lou , Xu Yuan , Nian-Feng Tzeng

Matching the performance of conditional Generative Adversarial Networks with little supervision is an important task, especially in venturing into new domains. We design a new training algorithm, which is robust to missing or ambiguous…

Machine Learning · Statistics 2019-06-11 Kiran Koshy Thekumparampil , Sewoong Oh , Ashish Khetan

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an…

Machine Learning · Computer Science 2026-02-03 Samuel Nellessen , Tal Kachman

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…

Artificial Intelligence · Computer Science 2026-03-17 Yiling Tao , Xinran Zheng , Shuo Yang , Meiling Tao , Xingjun Wang

We study the problem of multi-agent multi-armed bandits with adversarial corruption in a heterogeneous setting, where each agent accesses a subset of arms. The adversary can corrupt the reward observations for all agents. Agents share these…

Machine Learning · Computer Science 2024-11-14 Fatemeh Ghaffari , Xuchuang Wang , Jinhang Zuo , Mohammad Hajiesmaili

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…

Machine Learning · Computer Science 2026-01-22 Amine Andam , Jamal Bentahar , Mustapha Hedabou

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the…

While generalist foundation models like Gemini and GPT-4o demonstrate impressive multi-modal competence, existing evaluations fail to test their intelligence in dynamic, interactive worlds. Static benchmarks lack agency, while interactive…

Artificial Intelligence · Computer Science 2025-09-30 Fuqing Bie , Shiyu Huang , Xijia Tao , Zhiqin Fang , Leyi Pan , Junzhe Chen , Min Ren , Liuyu Xiang , Zhaofeng He

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g.,…

Multiagent Systems · Computer Science 2026-04-29 Jianming Chen , Yawen Wang , Junjie Wang , Xiaofei Xie , Yuanzhe Hu , Qing Wang , Fanjiang Xu

Existing works have made great progress in improving adversarial robustness, but typically test their method only on data from the same distribution as the training data, i.e. in-distribution (ID) testing. As a result, it is unclear how…

Machine Learning · Computer Science 2024-06-05 Lin Li , Yifei Wang , Chawin Sitawarin , Michael Spratling

The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However,…

Computation and Language · Computer Science 2024-08-28 Chi-Min Chan , Jianxuan Yu , Weize Chen , Chunyang Jiang , Xinyu Liu , Weijie Shi , Zhiyuan Liu , Wei Xue , Yike Guo

Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population learns. In order to design scalable algorithms for systems…

Optimization and Control · Mathematics 2020-02-24 Romuald Elie , Julien Pérolat , Mathieu Laurière , Matthieu Geist , Olivier Pietquin