Imagen de Portada

Guidelines for Applying RL and MARL in Cybersecurity Applications

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mavroudis, Vasilios, Palmer, Gregory, Farmer, Sara, Whitehead, Kez Smithson, Foster, David, Price, Adam, Miles, Ian, Caron, Alberto, Pasteris, Stephen
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Nearest Neighbour with Bandit Feedback
por: Pasteris, Stephen, et al.
Publicado: (2023)

Fairness with Exponential Weights
por: Pasteris, Stephen, et al.
Publicado: (2024)

Extraction Propagation
por: Pasteris, Stephen, et al.
Publicado: (2024)

Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learning
por: Wilson, Alec, et al.
Publicado: (2024)

Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
por: Pasteris, Stephen, et al.
Publicado: (2024)

On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
por: Caron, Alberto, et al.
Publicado: (2025)

Towards Causal Model-Based Policy Optimization
por: Caron, Alberto, et al.
Publicado: (2025)

A View on Out-of-Distribution Identification from a Statistical Testing Theory Perspective
por: Caron, Alberto, et al.
Publicado: (2024)

Zero-Trust Network Access (ZTNA)
por: Mavroudis, Vasilios
Publicado: (2024)

Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems
por: Kolicic, Benjamin, et al.
Publicado: (2024)

Less is more? Rewards in RL for Cyber Defence
por: Bates, Elizabeth, et al.
Publicado: (2025)

Entity-based Reinforcement Learning for Autonomous Cyber Defence
por: Thompson, Isaac Symes, et al.
Publicado: (2024)

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning
por: Vyas, Sanyam, et al.
Publicado: (2025)

HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation
por: Ristea, Dan, et al.
Publicado: (2024)

Analysis of Publicly Accessible Operational Technology and Associated Risks
por: Rodda, Matthew, et al.
Publicado: (2025)

Quantifying Mix Network Privacy Erosion with Generative Models
por: Mavroudis, Vasilios, et al.
Publicado: (2025)

Referential Security as a New Paradigm for AI Evaluations
por: Ristea, Dan, et al.
Publicado: (2026)

From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs
por: Abuadbba, Alsharif, et al.
Publicado: (2025)

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space
por: Vyas, Sanyam, et al.
Publicado: (2024)

Beyond Rewards in Reinforcement Learning for Cyber Defence
por: Bates, Elizabeth, et al.
Publicado: (2026)

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
por: McFadden, Shae, et al.
Publicado: (2026)

Environment Complexity and Nash Equilibria in a Sequential Social Dilemma
por: Yasir, Mustafa, et al.
Publicado: (2024)

Autonomous Network Defence using Reinforcement Learning
por: Foley, Myles, et al.
Publicado: (2024)

CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents
por: Emerson, Harry, et al.
Publicado: (2024)

MARL Warehouse Robots
por: Allman, Price, et al.
Publicado: (2025)

An Empirical Game-Theoretic Analysis of Autonomous Cyber-Defence Agents
por: Palmer, Gregory, et al.
Publicado: (2025)

Asymptomatic bacteriuria or symptomatic urinary tract infection? That is the question
por: Alejandro Smithson
Publicado: (2024)

‘It f**ked me up bad, man … It f**ked my head up, bad, man, bad’: The impact of Covid‐19 on children's mental health and well‐being in the youth justice system
por: Hannah Smithson
Publicado: (2024)

CONVERGENCIA ECONÓMICA EN LOS DEPARTAMENTOS DE MENDOZA
por: Elizabeth Pasteris
Publicado: (2016)

What if we could hot swap our Biometrics?
por: Crowcroft, Jon, et al.
Publicado: (2025)

An Attentive Graph Agent for Topology-Adaptive Cyber Defence
por: Sandoval, Ilya Orson, et al.
Publicado: (2025)

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
por: Tessera, Kale-ab Abebe, et al.
Publicado: (2024)

Differential Privacy in the Extensive-Form Bandit Problem
por: Pasteris, Stephen, et al.
Publicado: (2026)

Civismo y cultura política. ¿Cómo se practica la democracia en Chile? Algunas reflexiones en torno a la Encuesta de Estratificación Social 2009
por: Daniel Duhart Smithson
Publicado: (2010)

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
por: Rutherford, Alexander, et al.
Publicado: (2023)

LLM-Mediated Guidance of MARL Systems
por: Siedler, Philipp D., et al.
Publicado: (2025)

Applied Cybersecurity & Internet Governance
Publicado: (2023)

On the Contents and Utility of IoT Cybersecurity Guidelines
por: Chen, Jesse, et al.
Publicado: (2023)

What Is the Hybrid Library?
por: Oppenheim, Charles, et al.
Publicado: (1999)

Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse
por: Barrett, Steve, et al.
Publicado: (2025)