paper-with-me

홈 › Papers

A Unified Attack Detection Strategy for Multi-Agent Systems over Transient and Steady Stages

2025-01-07 · Jinming Gao, Yijing Wang, Wentao Zhang, Rui Zhao, Yang Shi, Zhiqiang Zuo

This paper proposes a unified detection strategy against three kinds of attacks for multi-agent systems (MASs) which is applicable to both transient and steady stages. For attacks on the communication layer, a watermarking-based detection scheme with KullbackLeibler (KL) divergence is designed. Different from traditional communication schemes, each agent transmits a message set containing two state values with different types of watermarking. It is found that the detection performance is determined by the relevant parameters of the watermarking signal. Unlike the existing detection manoeuvres, such a scheme is capable of transient and steady stages. For attacks on the agent layer, a convergence rate related detection approach is put forward. It is shown that the resilience of the considered system is characterized by the coefficient and offset of the envelope. For hybrid attacks, based on the above detection mechanisms, a general framework resorting to trusted agents is presented, which requires weaker graph conditions and less information transmission. Finally, an example associated with the platooning of connected vehicles is given to support the theoretical results.

📄 PDF Abstract BibTeX arXiv:2501.03496

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Distributed Detection and Mitigation of Biasing Attacks over Multi-Agent Networks

2021-09-20 · Mohammadreza Doostmohammadian, Houman Zarrabi, Hamid R. Rabiee, Usman A. Khan 외

This paper proposes a distributed attack detection and mitigation technique based on distributed estimation over a multi-agent network, where the agents take partial system measurements susceptible to (possible) biasing …

Novel Defense Strategy Against Zero-Dynamics Attack in Multi-Agent Systems

2019-09-16

This paper considers the defense strategy of strategic topology switching for the second-order multi-agent system under zero-dynamics attack (ZDA) whose attack-starting time is allowed to be not the initial time. We firs…

BARD-MARL: Byzantine-Agent Detection for Learned Communication in Multi-Agent Reinforcement Learning

2026-06-15 · Almond Kiruthu Murimi arxiv

Learned communication improves coordination in cooperative multi-agent reinforcement learning, but it also creates a trust problem: a trained policy may route information through agents that have become faulty or adversa…

Multi-agent Reinforcement Learning

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents

2026-05-05 · Ishrith Gowda arxiv

Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We formalize memory poisoning attacks on retrieval-augmented agents as a Sta…

Anomaly Detection

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models

2025-02-18 · Huawei Lin, Yingjie Lao, Tong Geng, Tan Yu 외

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from tradi…

Text Generation