Related papers: Enhancing Cloud Network Resilience via a Robust LL…

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…

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…

Machine learning (ML)-based network intrusion detection is susceptible to attacks that perturb malicious network flows to evade detection. Existing approaches to evaluating the robustness of these models rely on gradient-based optimization…

We develop a queueing-theoretic framework to model the temporal evolution of cyber-attack surfaces, where the number of active vulnerabilities is represented as the backlog of a queue. Vulnerabilities arrive as they are discovered or…

Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be…

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box…

Cloud computing environments are increasingly vulnerable to security threats such as distributed denial-of-service (DDoS) attacks and SQL injection. Traditional security mechanisms, based on rule matching and feature recognition, struggle…

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

Traditional Reinforcement Learning (RL) frameworks generally assume that the agent perceives the state of the underlying Markov process instantaneously and then takes actions accordingly. If the agent cannot directly observe the process,…

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

Reinforcement learning (RL) has been a promising essence in future 5G-beyond and 6G systems. Its main advantage lies in its robust model-free decision-making in complex and large-dimension wireless environments. However, most existing RL…

This paper addresses the challenges of rapid resource variation and highly uncertain task loads in cloud computing environments. It proposes an optimization method for elastic cloud resource scaling based on a multi-agent system. The method…

Cyber deception assists in increasing the attacker's budget in reconnaissance or any early phases of threat intrusions. In the past, numerous methods of cyber deception have been adopted, such as IP address randomization, the creation of…

Communication networks able to withstand hostile environments are critically important for disaster relief operations. In this paper, we consider a challenging scenario where drones have been compromised in the supply chain, during their…

Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks. However, existing LLM web agents heavily rely on expensive proprietary LLM APIs, while open LLMs lack the necessary…

Self-healing capability is one of the most critical factors for a resilient distribution system, which requires intelligent agents to automatically perform restorative actions online, including network reconfiguration and reactive power…

This paper presents a novel federated reinforcement learning (Fed-RL) methodology to enhance the cyber resiliency of networked microgrids. We formulate a resilient reinforcement learning (RL) training setup which (a) generates episodic…

In disaster scenarios, establishing robust emergency communication networks is critical, and unmanned aerial vehicles (UAVs) offer a promising solution to rapidly restore connectivity. However, organizing UAVs to form multi-hop networks in…

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…

While reinforcement learning (RL) has demonstrated remarkable success in enhancing large language models (LLMs), it has primarily focused on single-turn tasks such as solving math problems. Training effective web agents for multi-turn…