相关论文: PoolFlip: A Multi-Agent Reinforcement Learning Sec…

Cyber-Physical Systems play a critical role in the infrastructure of various sectors, including manufacturing, energy distribution, and autonomous transportation systems. However, their increasing connectivity renders them highly vulnerable…

Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation, we propose the Wolfpack Adversarial Attack framework,…

Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has shown remarkable success in solving complex non-cooperative…

Cybersecurity is increasingly threatened by advanced and persistent attacks. As these attacks are often designed to disable a system (or a critical resource, e.g., a user account) repeatedly, it is crucial for the defender to keep updating…

The need for autonomous and adaptive defense mechanisms has become paramount in the rapidly evolving landscape of cyber threats. Multi-Agent Deep Reinforcement Learning (MADRL) presents a promising approach to enhancing the efficacy and…

Multi-agent reinforcement learning has received significant interest in recent years notably due to the advancements made in deep reinforcement learning which have allowed for the developments of new architectures and learning algorithms.…

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach creates a mismatch --…

Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate existing and novel algorithms. Specifically, in multi-agent RL…

The increasing integration of Industrial IoT (IIoT) exposes critical cyber-physical systems to sophisticated, multi-stage attacks that elude traditional defenses lacking contextual awareness. This paper introduces L2M-AID, a novel framework…

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However,…

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment…

A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move…

Reinforcement learning (RL) has been demonstrated suitable to develop agents that play complex games with human-level performance. However, it is not understood how to effectively use RL to perform cybersecurity tasks. To develop such…

This paper handles a kind of strategic game called potential games and develops a novel learning algorithm Payoff-based Inhomogeneous Partially Irrational Play (PIPIP). The present algorithm is based on Distributed Inhomogeneous Synchronous…

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental…

Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly…

Multi-agent systems (MAS) built on multimodal large language models exhibit strong collaboration and performance. However, their growing openness and interaction complexity pose serious risks, notably jailbreak and adversarial attacks.…

Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual, iterative refinement of algorithmic baselines. Recently, evolutionary coding agents powered by…

Training a multi-agent reinforcement learning (MARL) algorithm is more challenging than training a single-agent reinforcement learning algorithm, because the result of a multi-agent task strongly depends on the complex interactions among…

We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). ReF-ER was shown to outperform state of the art algorithms for continuous control in problems ranging…