Adversarial Attacks in Cooperative AI

2021-11-29 · Ted Fujimoto, Arthur Paul Pedersen

Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation. If intelligent agents are to interact and work together to solve complex problems, methods that counter non-cooperative behavior are needed to facilitate the training of multiple agents. This is the goal of cooperative AI. Recent research in adversarial machine learning, however, shows that models (e.g., image classifiers) can be easily deceived into making inferior decisions. Meanwhile, an important line of research in cooperative AI has focused on introducing algorithmic improvements that accelerate learning of optimally cooperative behavior. We argue that prominent methods of cooperative AI are exposed to weaknesses analogous to those studied in prior machine learning research. More specifically, we show that three algorithms inspired by human-like social intelligence are, in principle, vulnerable to attacks that exploit weaknesses introduced by cooperative AI's algorithmic improvements and report experimental findings that illustrate how these vulnerabilities can be exploited in practice.

📄 PDF Abstract BibTeX arXiv:2111.14833

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Trust-Aware Resilient Control and Coordination of Connected and Automated Vehicles

2023-05-26 · H M Sabbir Ahmad, Ehsan Sabouni, Wei Xiao, Christos G. Cassandras 외

We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to navigate through a conflict area. Adversarial attacks such as Sybil attacks can cause safety violations resulting in collisio…

Navigate

Adversarial attacks in consensus-based multi-agent reinforcement learning

2021-03-11 · Martin Figura, Krishna Chaitanya Kosaraju, Vijay Gupta

Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature. In this work, we study the effect of adversarial attacks on a network that employs a conse…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Evaluating Robustness of Cooperative MARL

2021-09-29 · Nhan Pham, Lam M. Nguyen, Jie Chen, Thanh Lam Hoang 외

In recent years, a proliferation of methods were developed for multi-agent reinforcement learning (MARL). In this paper, we focus on evaluating the robustness of MARL agents in continuous control tasks. In particular, we…

continuous-control Continuous Control MuJoCo Multi-agent Reinforcement Learning+2

Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation

2021-11-12 · Martin Figura, Yixuan Lin, Ji Liu, Vijay Gupta

Adversarial attacks during training can strongly influence the performance of multi-agent reinforcement learning algorithms. It is, thus, highly desirable to augment existing algorithms such that the impact of adversaria…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adversarial Attacks on Cooperative Multi-agent Bandits

2023-11-03 · Jinhang Zuo, Zhiyao Zhang, Xuchuang Wang, Cheng Chen 외

Cooperative multi-agent multi-armed bandits (CMA2B) consider the collaborative efforts of multiple agents in a shared multi-armed bandit game. We study latent vulnerabilities exposed by this collaboration and consider ad…

Multi-Armed Bandits