arXiv Machine Learning June 26, 2026 By Raphael Simon, Pieter Libin, Wim Mees

Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation

Read the original on arXiv Machine Learning →

arXiv:2509. 20008v2 Announce Type: replace Abstract: Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 26

NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing

arXiv:2603. 19864v2 Announce Type: replace Abstract: Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces.

By Raphael Simon, Jos\'e Carrasquel, Wim Mees, Pieter Libin

reinforcement-learning efficiency

arXiv AI

Jun 17

Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents

arXiv:2606. 18223v1 Announce Type: cross Abstract: With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained via Reinforcement Learning (RL).

By Ankita Samaddar, Sandeep Neema, Daniel Balasubramanian, Xenofon Koutsoukos

agents reinforcement-learning

arXiv Machine Learning

Jul 24

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.

By Chenlong Yin, Runpeng Geng, Yanting Wang, Jinyuan Jia

llms agents reinforcement-learning efficiency benchmarks safety

arXiv AI

Aug 18

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

arXiv:2608. 15016v1 Announce Type: cross Abstract: Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into reliable system commands.

By Yiran Gao, Juntao Chen, Tao Li

llms agents fine-tuning

arXiv Machine Learning

Jul 15

NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions

arXiv:2604. 09523v2 Announce Type: replace Abstract: Training reinforcement-learning agents for cyber defense requires an environment that reflects the operational setting: noisy, partial observations, several defenders coordinating across a network, and an adaptive adversary realized through self-play.

By Igor Jankowski

rag agents reinforcement-learning

arXiv Machine Learning

5d ago

Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System

The paper introduces a new method for generating universal adversarial perturbations (UAPs) against deep reinforcement learning (DRL)-based intrusion detection systems (IDS). It leverages Probabilistic Robustness (PR) as a post‑hoc metric to guide UAP creation, integrating PR directly into the optimization objective. The authors further develop PX‑UAP, which incorporates explainable AI (XAI) to shape perturbations within realistic domain constraints, and provide a theoretical analysis of its design. Experiments show PX‑UAP outperforms existing UAP techniques in attack effectiveness.

By Hongsen Zhang, Lu Zhang, Mingjing Xu, Yi Zhang, Gregory Epiphaniou, Carsten Maple

reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing

Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions

Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System