# Robust Communicative Multi-Agent Reinforcement Learning with Active Defense

arXiv: https://arxiv.org/abs/2312.11545 · HTML: https://mlsanity.com/paper/2312.11545/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 16 Dec 2023.

## Builds on (most cited first, 14 of 14)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Adversarial Attacks On Multi-Agent Communication](https://mlsanity.com/paper/2101.06560/) (2021)
- [Robust Multi-Agent Reinforcement Learning with State Uncertainty](https://mlsanity.com/paper/2307.16212/) (2023)
- [Learning Selective Communication for Multi-Agent Path Finding](https://mlsanity.com/paper/2109.05413/) (2021)
- [Succinct and Robust Multi-Agent Communication With Temporal Message Control](https://mlsanity.com/paper/2010.14391/) (2020)
- [Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning](https://mlsanity.com/paper/2108.03803/) (2021)
- [Online Robust Policy Learning in the Presence of Unknown Adversaries](https://mlsanity.com/paper/1807.06064/) (2018)
- [Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation](https://mlsanity.com/paper/2305.05116/) (2023)

## Built on by (most cited first, 5 of 5)

- [Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies](https://mlsanity.com/paper/2512.16167/) (2025)
- [PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2605.23027/) (2026)
- [IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems](https://mlsanity.com/paper/2410.16237/) (2024)
- [Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space](https://mlsanity.com/paper/2508.15764/) (2025)
- [Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization](https://mlsanity.com/paper/2602.11437/) (2026)

## Abstract (arXiv)

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 to develop robust communicative MARL technique. However, existing research in this domain has predominantly focused on passive defense strategies, where agents receive all messages equally, making it hard to balance performance and robustness. We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision. There are two challenges to implement this strategy, that are defining unreliable messages and adjusting the unreliable messages' impact on the final decision properly. To address them, we design an Active Defense Multi-Agent Communication framework (ADMAC), which estimates the reliability of received messages and adjusts their impact on the final decision accordingly with the help of a decomposable decision structure. The superiority of ADMAC over existing methods is validated by experiments in three communication-critical tasks under four types of attacks.