A Comprehensive Survey: Evaluating the Efficiency of Artificial Intelligence and Machine Learning Techniques on Cyber Security Solutions

M Ozkan-Ozay, E Akin, Ö Aslan, S Kosunalp… - IEEE …, 2024 - ieeexplore.ieee.org
Given the continually rising frequency of cyberattacks, the adoption of artificial intelligence
methods, particularly Machine Learning (ML), Deep Learning (DL), and Reinforcement …

Automated cyber defence: A review

S Vyas, J Hannay, A Bolton, PP Burnap - arXiv preprint arXiv:2303.04926, 2023 - arxiv.org
Within recent times, cybercriminals have curated a variety of organised and resolute cyber
attacks within a range of cyber systems, leading to consequential ramifications to private and …

Intrusion prevention through optimal stopping

K Hammar, R Stadler - IEEE Transactions on Network and …, 2022 - ieeexplore.ieee.org
We study automated intrusion prevention using reinforcement learning. Following a novel
approach, we formulate the problem of intrusion prevention as an (optimal) multiple stopping …

Comparative DQN-improved algorithms for stochastic games-based automated edge intelligence-enabled IoT malware spread-suppression strategies

Y Shen, C Shepherd, CM Ahmed… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
Massive volumes of malware spread incidents continue to occur frequently across the
Internet of Things (IoT). Owing to its self-learning and adaptive capability, artificial …

Digital twins for security automation

K Hammar, R Stadler - NOMS 2023-2023 IEEE/IFIP Network …, 2023 - ieeexplore.ieee.org
We present a novel emulation system for creating high-fidelity digital twins of IT
infrastructures. The digital twins replicate key functionality of the corresponding …

Learning near-optimal intrusion responses against dynamic attackers

K Hammar, R Stadler - IEEE Transactions on Network and …, 2023 - ieeexplore.ieee.org
We study automated intrusion response and formulate the interaction between an attacker
and a defender as an optimal stopping game where attack and defense strategies evolve …

Learning security strategies through game play and optimal stopping

K Hammar, R Stadler - arXiv preprint arXiv:2205.14694, 2022 - arxiv.org
We study automated intrusion prevention using reinforcement learning. Following a novel
approach, we formulate the interaction between an attacker and a defender as an optimal …

Nasimemu: Network attack simulator & emulator for training agents generalizing to novel scenarios

J Janisch, T Pevný, V Lisý - … Symposium on Research in Computer Security, 2023 - Springer
Current frameworks for training offensive penetration testing agents with deep reinforcement
learning struggle to produce agents that perform well in real-world scenarios, due to the …

Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search

K Hammar, N Dhir, R Stadler - arXiv preprint arXiv:2407.11070, 2024 - arxiv.org
The CAGE-2 challenge is considered a standard benchmark to compare methods for
autonomous cyber defense. Current state-of-the-art methods evaluated against this …

Scalable learning of intrusion response through recursive decomposition

K Hammar, R Stadler - International Conference on Decision and Game …, 2023 - Springer
We study automated intrusion response for an IT infrastructure and formulate the interaction
between an attacker and a defender as a partially observed stochastic game. To solve the …